© 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. 125169
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    This neuron responds to structural markup and JSON‐format tokens (e.g. section keys like "unrelated_skills" or control tokens such as <|start_header_id|>).

    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
     NTN
    -0.07
    bite
    -0.06
    INGTON
    -0.06
     ymin
    -0.06
    ]){
    -0.06
    INGER
    -0.06
    نز
    -0.06
     Ấ
    -0.06
    (NULL
    -0.06
    OLID
    -0.06
    POSITIVE LOGITS
     nhánh
    0.06
     diy
    0.06
    ully
    0.06
    Formula
    0.06
    .ix
    0.06
     notoriously
    0.06
    _CT
    0.06
    venient
    0.06
    наслідок
    0.06
    _utc
    0.06
    Activations Density 0.005%

    No Known Activations