© 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. 95243
    Prev
    Next
    INDEX
    Explanations

    in

    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
     butterflies
    -0.06
    roller
    -0.06
     calculations
    -0.06
    .valueOf
    -0.06
    FragmentManager
    -0.06
     chart
    -0.06
    师
    -0.06
    OUTPUT
    -0.06
     博
    -0.06
     pinMode
    -0.05
    POSITIVE LOGITS
     continual
    0.07
     velké
    0.07
     Recommend
    0.06
    Review
    0.06
    vor
    0.06
     instruct
    0.06
    oris
    0.06
     perv
    0.06
    ề
    0.06
     neob
    0.06
    Activations Density 0.004%

    No Known Activations