© 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
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 5578
    Prev
    Next
    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sắp
    -0.07
    emple
    -0.07
    ัตถ
    -0.07
     predator
    -0.06
    IGHLIGHT
    -0.06
    ın
    -0.06
     Expert
    -0.06
     prostitut
    -0.06
     закры
    -0.06
    _basis
    -0.06
    POSITIVE LOGITS
    .navCtrl
    0.07
    PH
    0.07
    Smith
    0.06
     with
    0.06
    _agg
    0.06
     LIKE
    0.06
     worms
    0.06
    Analysis
    0.06
     joined
    0.06
    MH
    0.06
    Activations Density 0.004%

    No Known Activations