© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12679
    Prev
    Next
    INDEX
    Explanations

    common words

    np_max-act · gemini-2.0-flash

    This neuron strongly activates on terms related to child-development stages and toddler behavior (e.g. child psychology, toddler, “The No Stage,” etc.).

    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
     Literary
    -0.07
     Narrow
    -0.07
     strips
    -0.06
     princess
    -0.06
     Lost
    -0.06
    estro
    -0.06
    getState
    -0.06
     Alf
    -0.06
     PIX
    -0.06
     Laur
    -0.06
    POSITIVE LOGITS
    ijing
    0.07
     fayd
    0.07
    (cn
    0.07
     OUTER
    0.07
    can
    0.06
    _BLOCKS
    0.06
    ких
    0.06
     vyjád
    0.06
    _seg
    0.06
    .asInstanceOf
    0.06
    Activations Density 0.112%

    No Known Activations