© 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. 79543
    Prev
    Next
    INDEX
    Explanations

    struggling

    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
    eneral
    -0.07
     mythical
    -0.07
     memory
    -0.07
     Зав
    -0.06
    -day
    -0.06
     bew
    -0.06
    醴
    -0.06
     convened
    -0.06
    .setVertical
    -0.06
     saw
    -0.06
    POSITIVE LOGITS
     struggling
    0.15
     struggle
    0.13
     struggled
    0.12
     strugg
    0.11
     struggles
    0.10
    .adapters
    0.08
    -gl
    0.08
     Thr
    0.07
    .gg
    0.07
    .redis
    0.07
    Activations Density 0.009%

    No Known Activations