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. 8206
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron fires on inclusive, rally‐style phrases that pair “together” with “we” (e.g. “Together, we will…”).

    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
     orderBy
    -0.07
    UpdatedAt
    -0.07
     Abdul
    -0.07
    Agents
    -0.07
     horrified
    -0.07
    closed
    -0.07
     Voor
    -0.07
    ぬ
    -0.07
    apgolly
    -0.07
    ัปดาห
    -0.06
    POSITIVE LOGITS
     SUPER
    0.07
     found
    0.06
    Changing
    0.06
     Write
    0.06
     propensity
    0.06
    Gab
    0.06
    _fp
    0.06
     gemeins
    0.06
     measured
    0.06
     characters
    0.06
    Activations Density 0.011%

    No Known Activations