© 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. 91378
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
    ",
    ↵
    -0.06
    Cursor
    -0.06
     рекоменда
    -0.06
    	O
    -0.06
     ***
    -0.06
     cooperation
    -0.06
     نبود
    -0.06
     '').
    -0.06
     ahead
    -0.06
     безопас
    -0.06
    POSITIVE LOGITS
    Hope
    0.07
    assic
    0.06
     allerg
    0.06
     kidn
    0.06
     Identification
    0.06
     Vatican
    0.06
     cpf
    0.06
    Mathf
    0.06
     Phó
    0.06
     physical
    0.06
    Activations Density 0.004%

    No Known Activations