© 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. 110088
    Prev
    Next
    INDEX
    Explanations

    needs more context

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens or values (e.g. digits, measurements, IDs).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
     зап
    -0.06
    ,
    ↵
    -0.06
    ,↵
    -0.06
    .ast
    -0.06
    拿
    -0.06
     amnesty
    -0.06
     ama
    -0.06
    慎
    -0.06
     Ef
    -0.06
    Оп
    -0.06
    POSITIVE LOGITS
    ISIBLE
    0.07
    criptive
    0.07
    clear
    0.07
    Environmental
    0.06
    oracle
    0.06
    .job
    0.06
     Ethan
    0.06
    ogonal
    0.06
    ificación
    0.06
    immel
    0.06
    Activations Density 0.242%

    No Known Activations