© 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. 7-RESID-POST-AA
    6. 32154
    Prev
    Next
    INDEX
    Explanations

    22

    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
    ational
    -0.07
    .jd
    -0.07
     hành
    -0.06
     nâng
    -0.06
    姉
    -0.06
    itate
    -0.06
    альних
    -0.06
     Sponge
    -0.06
     jim
    -0.06
    ática
    -0.06
    POSITIVE LOGITS
     contacting
    0.07
     companies
    0.06
    302
    0.06
     odpově
    0.06
    .getSharedPreferences
    0.06
    删除
    0.06
     fixed
    0.06
    422
    0.06
     keeping
    0.06
     given
    0.06
    Activations Density 0.006%

    No Known Activations