© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 55541
    Prev
    Next
    INDEX
    Explanations

    programming and technology

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of “tool” (and related forms like “tools”), signaling references to selecting or using a tool.

    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
    galement
    -0.06
    .Width
    -0.06
    Validity
    -0.06
     territory
    -0.06
     clips
    -0.06
    水
    -0.06
    ันเป
    -0.06
     UserDefaults
    -0.06
     chịu
    -0.06
     mirac
    -0.06
    POSITIVE LOGITS
     ******************************************************************************↵
    0.07
     ����
    0.07
    ?.
    0.07
     
    0.06
    VOID
    0.06
    quire
    0.06
    [I
    0.06
    fant
    0.06
     коман
    0.06
    _CITY
    0.06
    Activations Density 0.012%

    No Known Activations