© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 36868
    Prev
    Next
    INDEX
    Explanations

    War

    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
    ��
    -0.08
    -mile
    -0.07
     scriptures
    -0.06
     formatter
    -0.06
    ptive
    -0.06
    	placeholder
    -0.06
     Grants
    -0.06
     duygu
    -0.06
     hostel
    -0.06
    .checkNotNull
    -0.06
    POSITIVE LOGITS
    _unix
    0.07
    ogonal
    0.07
    (dom
    0.06
    Impl
    0.06
     requester
    0.06
    (DATA
    0.06
     bezier
    0.06
    완료
    0.06
     attr
    0.06
    واج
    0.06
    Activations Density 0.097%

    No Known Activations