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. 130701
    Prev
    Next
    INDEX
    Explanations

    virus

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on occurrences of the token “virus.”

    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
    ματο
    -0.07
    lası
    -0.07
     김
    -0.06
    Preparing
    -0.06
     coming
    -0.06
     Belmont
    -0.06
    MainFrame
    -0.06
     working
    -0.06
    _glob
    -0.06
    增加
    -0.06
    POSITIVE LOGITS
     Bytes
    0.07
    oken
    0.07
    児
    0.07
    ENABLE
    0.06
     خون
    0.06
    (pat
    0.06
     crater
    0.06
     traj
    0.06
    ????
    0.06
     SSE
    0.06
    Activations Density 0.383%

    No Known Activations