© 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
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 32006
    Prev
    Next
    INDEX
    Explanations

    MA PA

    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
    と思
    -0.08
    except
    -0.07
     except
    -0.07
     друз
    -0.07
     punctuation
    -0.06
    इन
    -0.06
     either
    -0.06
    ith
    -0.06
    üml
    -0.06
    intr
    -0.06
    POSITIVE LOGITS
    CA
    0.13
     CA
    0.13
     DA
    0.13
    BA
    0.13
     FA
    0.12
     MA
    0.11
     SA
    0.11
     PA
    0.11
    VA
    0.11
    TA
    0.11
    Activations Density 0.068%

    No Known Activations