© 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. 19-RESID-POST-AA
    11. 31831
    Prev
    Next
    INDEX
    Explanations

    Criteria

    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
    くれる
    -0.07
     Plant
    -0.07
    816
    -0.07
    件事
    -0.07
    Plant
    -0.06
     thaimassage
    -0.06
    在线观看
    -0.06
     nối
    -0.06
    lightbox
    -0.06
     entrega
    -0.06
    POSITIVE LOGITS
     criteria
    0.10
     criterion
    0.10
     Criteria
    0.10
    rror
    0.07
     crit
    0.07
     기준
    0.07
    atri
    0.07
    cir
    0.07
    ula
    0.07
     cues
    0.07
    Activations Density 0.007%

    No Known Activations