© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91485
    Prev
    Next
    INDEX
    Explanations

    referring above

    np_max-act · gemini-2.0-flash

    The neuron detects cross‐references to earlier text, i.e. phrases like “as mentioned above.”

    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
    _series
    -0.08
    ascular
    -0.08
    ication
    -0.07
     highlighting
    -0.07
    _Bar
    -0.06
     відповід
    -0.06
     thirsty
    -0.06
     examine
    -0.06
    grounds
    -0.06
     Publisher
    -0.06
    POSITIVE LOGITS
    Motor
    0.06
     TextStyle
    0.06
     iphone
    0.06
     (*((
    0.06
     друж
    0.06
    렇
    0.06
     giriş
    0.06
     düşür
    0.06
     *)
    0.06
    Hu
    0.06
    Activations Density 0.021%

    No Known Activations