© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43310
    Prev
    Next
    INDEX
    Explanations

    baby

    np_max-act · gemini-2.0-flash

    This neuron responds to words referring to childbirth or pregnancy (e.g. baby, birth, pregnant, giving).

    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
    。在
    -0.07
    _when
    -0.07
    _sa
    -0.07
     runner
    -0.06
     warehouses
    -0.06
     Provision
    -0.06
    Protection
    -0.06
     WWW
    -0.06
    iệm
    -0.06
    *m
    -0.06
    POSITIVE LOGITS
    .XRTableCell
    0.07
    Refs
    0.07
     CircularProgress
    0.07
     prolonged
    0.07
    іїв
    0.06
     nour
    0.06
    PDOException
    0.06
     leo
    0.06
    moduleId
    0.06
    štění
    0.06
    Activations Density 0.011%

    No Known Activations