Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 34835
    Prev
    Next
    INDEX
    Explanations

    marking

    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
     Burns
    -0.07
    andan
    -0.07
     Utility
    -0.07
     Atlantic
    -0.06
    reements
    -0.06
     dog
    -0.06
     utilities
    -0.06
    ué
    -0.06
     Chess
    -0.06
     abused
    -0.06
    POSITIVE LOGITS
    북도
    0.08
    hands
    0.07
    _VOL
    0.07
    ــ
    0.07
    .gson
    0.07
    ตน
    0.07
     đu
    0.07
     '~/
    0.07
    θεια
    0.06
    �
    0.06
    Activations Density 0.022%

    No Known Activations