Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1472
    Prev
    Next
    INDEX
    Explanations

    Random text with @

    np_max-act · gemini-2.0-flash

    The neuron flags numeric tokens—especially decimal numbers or measurements—within the text.

    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
    _traffic
    -0.07
     SimpleName
    -0.07
     Weg
    -0.07
    tgt
    -0.07
    timezone
    -0.06
    dance
    -0.06
    _ends
    -0.06
    -shopping
    -0.06
    /jpeg
    -0.06
     Digital
    -0.06
    POSITIVE LOGITS
    addle
    0.06
     siguientes
    0.06
    okane
    0.06
     handguns
    0.06
     anchored
    0.05
     classe
    0.05
    té
    0.05
    [arr
    0.05
     �
    0.05
    Denver
    0.05
    Activations Density 0.174%

    No Known Activations