© 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. 52030
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Intelligence
    -0.07
     sustainable
    -0.07
     Seamless
    -0.07
     statically
    -0.07
     twins
    -0.06
    uation
    -0.06
     laundry
    -0.06
     polymer
    -0.06
     Memo
    -0.06
    loaded
    -0.06
    POSITIVE LOGITS
    Với
    0.07
     ++)↵
    0.07
     Với
    0.07
     kterého
    0.07
    ุค
    0.06
    ματα
    0.06
     với
    0.06
     spep
    0.06
     Alv
    0.06
    صح
    0.06
    Activations Density 0.145%

    No Known Activations