© 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. 19-RESID-POST-AA
    6. 118643
    Prev
    Next
    INDEX
    Explanations

    possessive/contraction "'s" or "is"

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     professionnel
    -0.07
    Entity
    -0.07
     Volume
    -0.07
    няется
    -0.07
     pemb
    -0.07
    aram
    -0.06
    orie
    -0.06
    Images
    -0.06
     söyl
    -0.06
    Detailed
    -0.06
    POSITIVE LOGITS
    ("{
    0.06
    .w
    0.06
     팬
    0.06
    िर
    0.06
    .slider
    0.06
    ठन
    0.06
    ษายน
    0.06
    .offsetWidth
    0.06
    /slider
    0.06
     И
    0.06
    Activations Density 0.061%

    No Known Activations