© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 121281
    Prev
    Next
    INDEX
    Explanations

    very

    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
    .issue
    -0.07
    (P
    -0.06
     maxlen
    -0.06
    -save
    -0.06
     Ads
    -0.06
     libr
    -0.06
    agn
    -0.06
     regular
    -0.06
    (off
    -0.06
    leaders
    -0.06
    POSITIVE LOGITS
     very
    0.13
     نويسنده
    0.08
    very
    0.08
     VERY
    0.08
     Very
    0.08
    Very
    0.07
     Daha
    0.07
    _ipv
    0.07
    VERY
    0.06
     πολύ
    0.06
    Activations Density 0.036%

    No Known Activations