© 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. 3-RESID-POST-AA
    11. 122998
    Prev
    Next
    INDEX
    Explanations

    spend

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     três
    -0.07
     utf
    -0.07
     enjoying
    -0.07
     White
    -0.07
     outro
    -0.06
     části
    -0.06
     bright
    -0.06
    .example
    -0.06
     called
    -0.06
     young
    -0.06
    POSITIVE LOGITS
    pend
    0.24
     Spend
    0.18
     Pend
    0.13
    PEND
    0.13
     pend
    0.13
     Depend
    0.08
     Predicate
    0.08
    prepend
    0.08
     spend
    0.07
    станов
    0.07
    Activations Density 0.006%

    No Known Activations