© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92518
    Prev
    Next
    INDEX
    Explanations

    ant

    np_max-act · gemini-2.0-flash

    The neuron never activates—it does not respond to any tokens.

    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
    失败
    -0.06
    aims
    -0.06
     halk
    -0.06
     fasta
    -0.06
     总
    -0.06
     Wolf
    -0.06
    _FC
    -0.06
     fragmentation
    -0.05
    .Se
    -0.05
    )",↵
    -0.05
    POSITIVE LOGITS
     bright
    0.07
    เตอร
    0.07
    getParameter
    0.07
     applied
    0.07
    	             
    0.07
     thứ
    0.07
     dem
    0.07
    ارک
    0.06
     misplaced
    0.06
     ~
    0.06
    Activations Density 0.003%

    No Known Activations