© 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. 25889
    Prev
    Next
    INDEX
    Explanations

    questions or troubleshooting

    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_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
     Pool
    -0.06
     Qui
    -0.06
    �
    -0.06
    Solution
    -0.06
     compressor
    -0.06
    Add
    -0.06
    avig
    -0.06
     pool
    -0.06
     terminator
    -0.06
    perienced
    -0.06
    POSITIVE LOGITS
    ])->
    0.07
    gable
    0.06
     finans
    0.06
     pilgr
    0.06
    !!↵↵
    0.06
    !↵↵
    0.06
     ministry
    0.06
    ليزية
    0.06
    yah
    0.06
    IÓN
    0.06
    Activations Density 0.071%

    No Known Activations