© 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. 128759
    Prev
    Next
    INDEX
    Explanations

    chemicals and health concerns

    np_max-act · gemini-2.0-flash

    references to endocrine disruptors and their health implications.

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

    The neuron fires on causal‐explanatory phrasing—especially “Because of …” and similar cause-and-effect connectors introducing reasons or consequences.

    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
     pain
    -0.07
     Binary
    -0.07
    أن
    -0.06
    Degree
    -0.06
     propagation
    -0.06
    Ian
    -0.06
    SceneManager
    -0.06
    touch
    -0.06
    جو
    -0.06
     Out
    -0.06
    POSITIVE LOGITS
    idual
    0.07
     Nr
    0.07
    -ul
    0.06
    upro
    0.06
    \Database
    0.06
    üfus
    0.06
     babel
    0.06
    iosper
    0.06
    .Back
    0.06
     devlet
    0.06
    Activations Density 0.042%

    No Known Activations