© 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
    7. Resid Post - 131k
    9. 27-RESID-POST-AA
    11. 60335
    Prev
    Next
    INDEX
    Explanations

    .doc

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Technical
    -0.08
    Definition
    -0.08
     lax
    -0.07
     drops
    -0.07
    Fake
    -0.07
     frustration
    -0.07
     trap
    -0.07
     camera
    -0.07
     traps
    -0.07
    ало
    -0.06
    POSITIVE LOGITS
     �
    0.07
    ENOMEM
    0.07
     �
    0.06
     zách
    0.06
    elier
    0.06
     αποτε
    0.06
     začí
    0.06
     характ
    0.06
    ůž
    0.06
     депут
    0.06
    Activations Density 0.006%

    No Known Activations