© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126839
    Prev
    Next
    INDEX
    Explanations

    save

    np_max-act · gemini-2.0-flash

    The neuron activates on phrases describing a hero’s mission to save the world (e.g., “save the world from…”).

    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
    /desktop
    -0.07
     shadow
    -0.06
     '+'
    -0.06
    )))))↵
    -0.06
     terk
    -0.06
     LIMIT
    -0.06
     Fakült
    -0.06
    oter
    -0.06
    AreaView
    -0.06
     původ
    -0.06
    POSITIVE LOGITS
    稱
    0.07
     texting
    0.06
    elere
    0.06
    rapped
    0.06
    ovel
    0.06
    HZ
    0.06
     analogy
    0.06
    neum
    0.06
    _sn
    0.06
     layers
    0.06
    Activations Density 0.011%

    No Known Activations