© 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. 89884
    Prev
    Next
    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash

    The neuron activates on phrases that introduce or cite supporting evidence or reasoning (e.g. “Based on …”).

    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
     pain
    -0.08
    ANGUAGE
    -0.07
    confidence
    -0.07
     Vall
    -0.07
    _capture
    -0.06
     rebel
    -0.06
     side
    -0.06
    CEPTION
    -0.06
     nale
    -0.06
     vlan
    -0.06
    POSITIVE LOGITS
     bugün
    0.07
     tyres
    0.06
    ARIO
    0.06
     insanely
    0.06
    ışma
    0.06
    >';↵
    0.06
    !"
    0.06
     HTTPS
    0.06
     éc
    0.06
    asics
    0.06
    Activations Density 0.036%

    No Known Activations