© 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. 109686
    Prev
    Next
    INDEX
    Explanations

    difficult

    np_max-act · gemini-2.0-flash

    The neuron activates on words that describe something as difficult or challenging.

    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
     FHA
    -0.07
      		
    -0.07
    ]',↵
    -0.07
    >'↵
    -0.07
     Fame
    -0.06
    ":
    -0.06
    :^{↵
    -0.06
    756
    -0.06
    /'+
    -0.06
    (fin
    -0.06
    POSITIVE LOGITS
     Npgsql
    0.07
    lient
    0.07
    aint
    0.06
    (stage
    0.06
    Listen
    0.06
    Leader
    0.06
    ailing
    0.06
    っぱ
    0.06
     revised
    0.06
    浩
    0.06
    Activations Density 0.060%

    No Known Activations