© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55817
    Prev
    Next
    INDEX
    Explanations

    lob

    np_max-act · gemini-2.0-flash

    functions and classes related to neural network layers, specifically for operations typically seen in deep learning frameworks.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is triggered by C++ template code referring to “Blob” (e.g. vector<Blob<Dtype>> and caffe/blob.hpp inclusions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RowAnimation
    -0.06
    (accounts
    -0.06
     REV
    -0.06
    (al
    -0.06
     παν
    -0.06
    mur
    -0.06
     newItem
    -0.06
    WithName
    -0.06
    @NoArgsConstructor
    -0.06
     administered
    -0.06
    POSITIVE LOGITS
    Possible
    0.07
    romium
    0.07
    慶
    0.06
    bsite
    0.06
    visualization
    0.06
    .local
    0.06
     diving
    0.06
     ekonomik
    0.06
    -date
    0.06
    .notification
    0.06
    Activations Density 0.002%

    No Known Activations