Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 84438
    Prev
    Next
    INDEX
    Explanations

    reaction

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on substrings related to “action,” for example in words like “reaction.”

    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
    ‌پ
    -0.07
    隐
    -0.06
     ricerca
    -0.06
    (Buffer
    -0.06
    [d
    -0.06
     tantal
    -0.06
     woods
    -0.06
    ülük
    -0.06
     Knowledge
    -0.06
    Exercise
    -0.06
    POSITIVE LOGITS
     responses
    0.08
     reacting
    0.08
     react
    0.08
     Reaction
    0.08
     Responses
    0.07
     reacts
    0.07
     response
    0.07
    ]"↵
    0.07
     reaction
    0.07
     responds
    0.07
    Activations Density 0.030%

    No Known Activations