© 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. 7867
    Prev
    Next
    INDEX
    Explanations

    excipients

    np_max-act · gemini-2.0-flash

    This neuron activates on terms naming formulation ingredients or additives (e.g., excipients, solvents).

    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
     Hot
    -0.06
     RIGHTS
    -0.06
    arga
    -0.06
     manganese
    -0.06
    Procedure
    -0.06
     다시
    -0.06
     depth
    -0.06
     trou
    -0.06
     FORM
    -0.05
    DidChange
    -0.05
    POSITIVE LOGITS
     oversees
    0.07
    ения
    0.07
    _inner
    0.07
    ?(
    0.07
    <>(
    0.06
     annex
    0.06
     :,
    0.06
    .Query
    0.06
    .cert
    0.06
    itet
    0.06
    Activations Density 0.003%

    No Known Activations