© 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
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 93918
    Prev
    Next
    INDEX
    Explanations

    Code/Data

    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
    *j
    -0.08
     đen
    -0.08
    -j
    -0.07
    j
    -0.07
     Gems
    -0.07
     j
    -0.07
    ejs
    -0.07
    .J
    -0.07
    J
    -0.07
     pedigree
    -0.07
    POSITIVE LOGITS
    <\/
    0.07
     TRAN
    0.06
     คร
    0.06
     nurt
    0.06
    ับผ
    0.06
     prepares
    0.06
     sneakers
    0.06
    	close
    0.06
    arsimp
    0.06
     акку
    0.06
    Activations Density 0.220%

    No Known Activations