© 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. 23-RESID-POST-AA
    11. 7874
    Prev
    Next
    INDEX
    Explanations

    alloc

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     throat
    -0.06
    499
    -0.06
     arp
    -0.06
    .getTag
    -0.06
     pathway
    -0.06
     normalization
    -0.06
     Ter
    -0.06
    以
    -0.05
     coercion
    -0.05
     få
    -0.05
    POSITIVE LOGITS
     νεφοκ
    0.07
    ):\
    0.07
    .toLowerCase
    0.07
    _PIN
    0.07
     hoàng
    0.07
    nické
    0.06
     Surgical
    0.06
    íf
    0.06
    (ans
    0.06
    rico
    0.06
    Activations Density 0.002%

    No Known Activations