© 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. 19-RESID-POST-AA
    11. 35470
    Prev
    Next
    INDEX
    Explanations

    client

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Combine
    -0.07
    /static
    -0.07
    	Type
    -0.07
    ующ
    -0.06
     conclusion
    -0.06
     Metropolitan
    -0.06
     TEXT
    -0.06
     takové
    -0.06
    iferay
    -0.06
    範
    -0.06
    POSITIVE LOGITS
    ظٹ
    0.07
     Aless
    0.07
    (lst
    0.07
    캐
    0.07
    leftJoin
    0.06
    juries
    0.06
     Morr
    0.06
     investigating
    0.06
    mm
    0.06
     AJ
    0.06
    Activations Density 0.002%

    No Known Activations