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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1651
    Prev
    Next
    INDEX
    Explanations

    > and

    np_max-act · gemini-2.0-flash

    Explanation of neuron 4 behavior: the main thing this neuron does is find version‐number tokens (numeric strings, especially those in version fields).

    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
    STOP
    -0.07
    iance
    -0.07
     refused
    -0.06
    046
    -0.06
    760
    -0.06
     Premi
    -0.06
     DAYS
    -0.06
     undue
    -0.06
    .Stop
    -0.06
    asıyla
    -0.06
    POSITIVE LOGITS
     чи
    0.07
    Analy
    0.07
    (PyObject
    0.06
     Clem
    0.06
     lights
    0.06
     ech
    0.06
     graves
    0.06
     Sky
    0.06
    /browser
    0.06
     phy
    0.06
    Activations Density 0.011%

    No Known Activations