© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109804
    Prev
    Next
    INDEX
    Explanations

    .Module

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the PyTorch base‐module identifier “nn.Module,” i.e. when defining a model class that inherits from nn.Module.

    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
    universal
    -0.08
    })↵↵↵
    -0.07
    Actions
    -0.07
    Count
    -0.07
     cheapest
    -0.07
    )))↵↵
    -0.06
    .peer
    -0.06
     pap
    -0.06
    (pat
    -0.06
    ')↵↵↵
    -0.06
    POSITIVE LOGITS
    Hi
    0.06
    McC
    0.06
     leagues
    0.06
     mitigation
    0.06
    іб
    0.06
     sidelined
    0.06
     judgment
    0.06
    ために
    0.06
    .Module
    0.06
    δο
    0.06
    Activations Density 0.000%

    No Known Activations