© 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 (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 35987
    Prev
    Next
    INDEX
    Explanations

    expression

    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
     tight
    -0.07
    анд
    -0.07
    하기
    -0.07
     modulo
    -0.06
     payable
    -0.06
    leted
    -0.06
    .DATE
    -0.06
    DDS
    -0.06
    (nil
    -0.06
    ingt
    -0.06
    POSITIVE LOGITS
     expression
    0.08
    	effect
    0.07
    eyes
    0.07
     French
    0.07
    Coroutine
    0.07
     oppression
    0.07
    _EXPORT
    0.07
    Prem
    0.07
    RESSION
    0.07
     Expression
    0.07
    Activations Density 0.012%

    No Known Activations