© 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 (Instruct)
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 7662
    Prev
    Next
    INDEX
    Explanations

    Beh

    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
    が
    -0.07
    klär
    -0.07
    (dictionary
    -0.07
     Oak
    -0.07
    ження
    -0.07
     tespit
    -0.07
    PARTMENT
    -0.06
    orbit
    -0.06
    čku
    -0.06
     ponds
    -0.06
    POSITIVE LOGITS
    -INF
    0.06
    σον
    0.06
    рис
    0.06
    HandlerContext
    0.06
    _VO
    0.06
    ़ि
    0.06
    umsuz
    0.06
    $arity
    0.06
    	AL
    0.06
    .al
    0.06
    Activations Density 0.001%

    No Known Activations