© 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. 11-RESID-POST-AA
    11. 52881
    Prev
    Next
    INDEX
    Explanations

    event

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Between
    -0.07
    .setEnabled
    -0.06
     آب
    -0.06
    oglobin
    -0.06
     optimism
    -0.06
    	strncpy
    -0.06
     прий
    -0.06
    xFF
    -0.06
     Compared
    -0.06
     thousand
    -0.06
    POSITIVE LOGITS
     event
    0.10
     events
    0.09
     EVENT
    0.08
     Event
    0.08
    企
    0.07
    EIF
    0.07
    活动
    0.07
     Organizations
    0.07
    onta
    0.07
     Events
    0.07
    Activations Density 0.016%

    No Known Activations