© 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. 129734
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron detects references to the presence or sufficiency of evidence in the record (e.g. “there was enough evidence in the record…”).

    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
     Scaling
    -0.07
    -Version
    -0.06
     名無し
    -0.06
    isspace
    -0.06
     disciples
    -0.06
    owitz
    -0.06
    channels
    -0.06
    -feedback
    -0.06
    rif
    -0.06
     Bulld
    -0.06
    POSITIVE LOGITS
     My
    0.07
     television
    0.07
     Kub
    0.07
    	M
    0.06
     bicy
    0.06
     Pics
    0.06
    _il
    0.06
    iciální
    0.06
     الح
    0.06
     чис
    0.06
    Activations Density 0.042%

    No Known Activations