© 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. 88179
    Prev
    Next
    INDEX
    Explanations

    holes or openings

    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
    isty
    -0.07
    	slot
    -0.06
    Mt
    -0.06
    TRY
    -0.06
     WARRANT
    -0.06
    _speed
    -0.06
    цеп
    -0.06
     call
    -0.06
     patrol
    -0.06
     \%
    -0.06
    POSITIVE LOGITS
    ()]);↵
    0.07
     için
    0.06
    ellido
    0.06
     lipstick
    0.06
    ?");↵
    0.06
    ))))↵↵
    0.06
     Ange
    0.06
     سمت
    0.06
     yaşında
    0.06
    (SYS
    0.06
    Activations Density 0.157%

    No Known Activations