Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 125670
    Prev
    Next
    INDEX
    Explanations

    programming questions

    np_max-act · gemini-2.0-flash

    This neuron fires on phrasing that gives advice or recommendations, marked by personal pronouns (“I,” “you”) and modal verbs (“should,” “can,” “must”).

    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
    거래
    -0.06
     그렇
    -0.06
    Storyboard
    -0.06
     Bannon
    -0.06
     Gy
    -0.06
    Iso
    -0.06
    streams
    -0.06
    textures
    -0.06
    clave
    -0.06
     Huge
    -0.06
    POSITIVE LOGITS
     interested
    0.07
    .Http
    0.07
    失败
    0.06
    DbType
    0.06
     willingness
    0.06
    =temp
    0.06
     Polo
    0.06
     destined
    0.06
     Revel
    0.06
     replied
    0.06
    Activations Density 0.194%

    No Known Activations