Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 129836
    Prev
    Next
    INDEX
    Explanations

    easily, efficiently

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _prec
    -0.09
    -aut
    -0.07
     reflux
    -0.07
     Technician
    -0.07
    оло
    -0.07
     широк
    -0.07
    _ir
    -0.07
     رج
    -0.07
     Comb
    -0.07
    Identification
    -0.06
    POSITIVE LOGITS
     запас
    0.06
    prak
    0.06
     MouseButton
    0.06
    gold
    0.06
     fas
    0.06
    _connected
    0.06
    $pdf
    0.06
     sperma
    0.06
     vyu
    0.05
     RaisePropertyChanged
    0.05
    Activations Density 0.045%

    No Known Activations