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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 19-RESID-POST-AA
    6. 59257
    Prev
    Next
    INDEX
    Explanations

    Alternative

    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
     $("
    -0.06
     Regex
    -0.06
     Kro
    -0.06
     sc
    -0.06
    ure
    -0.06
     وص
    -0.06
    esub
    -0.06
     EA
    -0.06
    .Cor
    -0.06
     scram
    -0.06
    POSITIVE LOGITS
     independ
    0.07
     eff
    0.07
     Seamless
    0.07
    lessly
    0.06
     picnic
    0.06
    -community
    0.06
    -gallery
    0.06
    yssey
    0.06
    .Print
    0.06
    ۱۹
    0.06
    Activations Density 0.000%

    No Known Activations