© 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. 44214
    Prev
    Next
    INDEX
    Explanations

    Scientific writing

    np_max-act · gemini-2.0-flash

    This neuron activates on numerical values and mathematical/formula tokens, i.e. parts of equations or numeric parameters.

    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
    (inter
    -0.07
     görüş
    -0.07
    _star
    -0.06
     Sect
    -0.06
    amentos
    -0.06
    ∧
    -0.06
     fra
    -0.06
    [word
    -0.06
     тру
    -0.06
    (classes
    -0.06
    POSITIVE LOGITS
    <AM
    0.07
     inside
    0.07
     속
    0.07
     metabolic
    0.06
     aktiv
    0.06
     Architect
    0.06
    	cerr
    0.06
     upset
    0.06
     unwind
    0.06
     photograph
    0.06
    Activations Density 0.018%

    No Known Activations