© 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. 776
    Prev
    Next
    INDEX
    Explanations

    mutation

    np_max-act · gemini-2.0-flash

    The neuron strongly responds to mentions of genetic mutations (e.g., “mutation,” “novel mutation,” “mutations”) in biomedical text.

    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
     �
    -0.08
    두
    -0.06
    oti
    -0.06
    student
    -0.06
    اور
    -0.06
     Amend
    -0.06
    cluding
    -0.06
    иф
    -0.06
    incorrect
    -0.06
    Kon
    -0.06
    POSITIVE LOGITS
     unbelievable
    0.06
    `.
    0.06
    "]↵↵
    0.06
    meth
    0.06
     Foley
    0.06
    }()↵↵
    0.06
     decorator
    0.06
     المهنة
    0.06
     crafts
    0.06
    Mutation
    0.06
    Activations Density 0.004%

    No Known Activations