© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129791
    Prev
    Next
    INDEX
    Explanations

    accumulator

    np_max-act · gemini-2.0-flash

    The neuron preferentially activates on uncommon technical or domain‐specific nouns and acronyms (i.e. specialized jargon terms).

    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
     About
    -0.07
    fprintf
    -0.07
     Andrea
    -0.06
    (comp
    -0.06
    ตอบ
    -0.06
     Six
    -0.06
     Answer
    -0.06
     shiny
    -0.06
    (get
    -0.06
    _cov
    -0.06
    POSITIVE LOGITS
    νος
    0.06
    Estado
    0.06
    ’à
    0.06
    _license
    0.06
     Tucker
    0.06
    ?',
    0.06
     relic
    0.06
    ная
    0.06
    ignant
    0.06
    τός
    0.06
    Activations Density 0.436%

    No Known Activations