© 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. 8820
    Prev
    Next
    INDEX
    Explanations

    stroke

    np_max-act · gemini-2.0-flash

    The neuron fires strongly on terms naming acute ischemic events (e.g. “acute,” “ischemic,” “stroke,” “infarction”) and thus detects mentions of acute medical conditions.

    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
    FileSync
    -0.06
     Clarence
    -0.06
     cut
    -0.06
    Cadastro
    -0.06
     timeline
    -0.06
     Vě
    -0.06
    	account
    -0.06
    _vector
    -0.06
    属于
    -0.06
    _buf
    -0.06
    POSITIVE LOGITS
    )、
    0.07
    のように
    0.07
    ＞
    0.06
     عنه
    0.06
    _OPER
    0.06
    tipo
    0.06
    Quiet
    0.06
     女
    0.06
    719
    0.06
     NSA
    0.06
    Activations Density 0.012%

    No Known Activations