© 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. 91607
    Prev
    Next
    INDEX
    Explanations

    mash

    np_max-act · gemini-2.0-flash

    The neuron identifies mentions of mashing or pureeing food (e.g., “mashed,” “mash,” “pureed”).

    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
    .breakpoints
    -0.07
    .signup
    -0.06
     luck
    -0.06
    ulet
    -0.06
     ValueType
    -0.06
    Blake
    -0.06
    _tl
    -0.06
     अग
    -0.06
    TimeString
    -0.06
    ">',↵
    -0.06
    POSITIVE LOGITS
     mashed
    0.07
     помощ
    0.06
    availability
    0.06
     abilities
    0.06
    _CID
    0.06
    és
    0.06
    average
    0.06
     access
    0.06
     Persons
    0.06
     empower
    0.06
    Activations Density 0.004%

    No Known Activations