Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 106753
    Prev
    Next
    INDEX
    Explanations

    best

    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
     layers
    -0.07
    _FAMILY
    -0.06
     infra
    -0.06
    axed
    -0.06
     SMS
    -0.06
     Uh
    -0.06
    FixedSize
    -0.06
     conclusion
    -0.06
    >}↵
    -0.06
    Ether
    -0.06
    POSITIVE LOGITS
     tomb
    0.07
    이는
    0.07
    Genesis
    0.06
    startIndex
    0.06
    ้ส
    0.06
    +"_
    0.06
     legit
    0.06
     Carlson
    0.06
     pré
    0.06
     pilgr
    0.06
    Activations Density 0.009%

    No Known Activations