© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9332
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    advice and remedies for managing medical conditions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron fires primarily on numeric and measurement tokens (e.g. numbers, decimal values, durations, and quantified data).

    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
    亭
    -0.06
    820
    -0.06
    	ref
    -0.06
    ым
    -0.06
    essel
    -0.06
    au
    -0.06
     unlocked
    -0.06
     blockers
    -0.06
    یشن
    -0.06
    LP
    -0.06
    POSITIVE LOGITS
     competitive
    0.07
     sustained
    0.07
    필
    0.07
     combustion
    0.07
     competitiveness
    0.06
     communications
    0.06
     proceeds
    0.06
    Foot
    0.06
    .constants
    0.06
     获取
    0.06
    Activations Density 0.043%

    No Known Activations