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. 99921
    Prev
    Next
    INDEX
    Explanations

    positive

    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
     calls
    -0.07
     remains
    -0.06
    壓
    -0.06
     用户
    -0.06
    —we
    -0.06
    acho
    -0.06
    verture
    -0.06
     markers
    -0.06
    utoff
    -0.06
     traps
    -0.06
    POSITIVE LOGITS
     karena
    0.07
    ouples
    0.07
    OwnerId
    0.07
    Rules
    0.06
     bapt
    0.06
    :.:.:
    0.06
     fieldValue
    0.06
    .ObjectMeta
    0.06
     Wong
    0.06
    241
    0.06
    Activations Density 0.009%

    No Known Activations