© 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. 89128
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on words expressing firm resolve or determination (e.g. “determined”).

    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
     pub
    -0.07
     KS
    -0.07
    ocks
    -0.07
     Prefix
    -0.06
     Gia
    -0.06
     Verm
    -0.06
     Beispiel
    -0.06
    Pair
    -0.06
     Gio
    -0.06
     ws
    -0.06
    POSITIVE LOGITS
     vowed
    0.08
     determined
    0.07
     채용
    0.07
    
    0.07
    ，而且
    0.07
    .Unmarshal
    0.07
     REPORT
    0.07
    cısı
    0.07
    落
    0.07
    DOWN
    0.07
    Activations Density 0.009%

    No Known Activations