© 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. 3-RESID-POST-AA
    11. 122988
    Prev
    Next
    INDEX
    Explanations

    thrombosis

    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
     pendant
    -0.06
     axiom
    -0.06
     меш
    -0.06
     hardness
    -0.06
     хорошо
    -0.06
     ion
    -0.06
    Ion
    -0.06
     PAGE
    -0.06
    应当
    -0.06
     strlen
    -0.06
    POSITIVE LOGITS
     первого
    0.07
     Included
    0.07
    imoto
    0.07
    croll
    0.07
    öm
    0.06
     Emb
    0.06
    ised
    0.06
    ServletContext
    0.06
     奥
    0.06
     throm
    0.06
    Activations Density 0.008%

    No Known Activations