© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92426
    Prev
    Next
    INDEX
    Explanations

    ivariate

    np_max-act · gemini-2.0-flash

    The neuron activates on technical mentions of metabolomic and multivariate data‐analysis methods (e.g. NMR spectroscopy, multivariate analysis, principal component analysis).

    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
    胎
    -0.07
    estructor
    -0.07
     ANAL
    -0.07
    mpar
    -0.06
     прис
    -0.06
    ็บ
    -0.06
     :]↵
    -0.06
     thắng
    -0.06
     Iz
    -0.06
    CriticalSection
    -0.06
    POSITIVE LOGITS
     length
    0.07
     Costume
    0.07
     ethnic
    0.07
     comprehension
    0.07
     Metallic
    0.06
     financially
    0.06
    _table
    0.06
    exam
    0.06
    Writing
    0.06
     Because
    0.06
    Activations Density 0.005%

    No Known Activations