© 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. 65910
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    Neuron 4 fires on words that introduce a noun phrase—i.e. determiners and quantifiers (articles like “a”/“un,” possessives like “my,” numerals like “two,” words like “some/bunch,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    requests for help with implementation and programming issues.

    oai_token-act-pair · gpt-4o-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
    MK
    -0.07
    ELSE
    -0.06
     sudah
    -0.06
    แรก
    -0.06
     꿈
    -0.06
     جزئ
    -0.06
    eği
    -0.06
     Cortex
    -0.06
     حذ
    -0.06
    年的
    -0.06
    POSITIVE LOGITS
     The
    0.06
    The
    0.06
    ;;↵↵
    0.06
     *}↵↵
    0.06
    <tag
    0.06
    .Primary
    0.06
     Each
    0.06
    +(
    0.06
    (tk
    0.06
     nisi
    0.06
    Activations Density 0.034%

    No Known Activations