© 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. 93967
    Prev
    Next
    INDEX
    Explanations

    해

    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
     returned
    -0.08
     prone
    -0.07
    기도
    -0.06
     Eine
    -0.06
     equiv
    -0.06
     granting
    -0.06
    _dirs
    -0.06
     Initiative
    -0.06
     adjunct
    -0.06
    (out
    -0.06
    POSITIVE LOGITS
    해
    0.30
     해
    0.18
    海
    0.11
    解
    0.09
     Hải
    0.08
     달
    0.08
    달
    0.08
     海
    0.08
    NSMutableDictionary
    0.08
     giải
    0.07
    Activations Density 0.001%

    No Known Activations