© 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. 3-RESID-POST-AA
    6. 121929
    Prev
    Next
    INDEX
    Explanations

    bullet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     visionary
    -0.07
     concatenated
    -0.07
     drops
    -0.07
    Teacher
    -0.07
     Copies
    -0.07
     سرم
    -0.06
    Ionic
    -0.06
     Trailer
    -0.06
    iton
    -0.06
    _gs
    -0.06
    POSITIVE LOGITS
     bullet
    0.19
     Bullet
    0.14
    Bullet
    0.10
    ULLET
    0.10
    bullet
    0.10
    _bullet
    0.09
    ullet
    0.08
    redient
    0.07
    	event
    0.06
    ++
    0.06
    Activations Density 0.002%

    No Known Activations