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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 75982
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
    ázal
    -0.08
    discount
    -0.08
    contest
    -0.08
    ']}'
    -0.07
     volunteered
    -0.07
    DOG
    -0.07
     Dropout
    -0.07
     Tokyo
    -0.07
     compagn
    -0.07
    emachine
    -0.07
    POSITIVE LOGITS
     Purs
    0.07
     gói
    0.06
     заклад
    0.06
    心
    0.06
     giải
    0.06
    _NATIVE
    0.06
     마음
    0.06
     церков
    0.06
    五月
    0.06
     Dro
    0.06
    Activations Density 0.013%

    No Known Activations