© 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. 55538
    Prev
    Next
    INDEX
    Explanations

    blood pressure

    np_max-act · gemini-2.0-flash

    terms related to hypertension and its impact on health, particularly in elderly populations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects terms referring to hypertension and blood‐pressure measurements or treatments.

    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
    kemiz
    -0.07
     зробити
    -0.06
    िछ
    -0.06
    _Current
    -0.06
    _frequency
    -0.06
    .Cell
    -0.06
    τεί
    -0.06
     را
    -0.06
     센
    -0.06
    nem
    -0.06
    POSITIVE LOGITS
     Candidates
    0.06
     Years
    0.06
    ivation
    0.06
     candidates
    0.06
    Place
    0.06
    (renderer
    0.06
     sex
    0.06
     spectators
    0.06
    :self
    0.06
    (settings
    0.06
    Activations Density 0.017%

    No Known Activations