© 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 (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 89519
    Prev
    Next
    INDEX
    Explanations

    oscill

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sank
    -0.07
     Valentine
    -0.07
    curity
    -0.07
     crippled
    -0.07
    	card
    -0.06
     deported
    -0.06
     gör
    -0.06
    INavigation
    -0.06
    _TMP
    -0.06
    <Boolean
    -0.06
    POSITIVE LOGITS
     Osc
    0.08
     oscill
    0.08
     oscillator
    0.07
    ObjectContext
    0.06
    ablish
    0.06
     fif
    0.06
    selling
    0.06
    chooser
    0.06
    alyzer
    0.06
    OSC
    0.06
    Activations Density 0.004%

    No Known Activations