© 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. 27-RESID-POST-AA
    11. 103938
    Prev
    Next
    INDEX
    Explanations

    "<"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,I
    -0.08
    cea
    -0.07
    Pay
    -0.07
    Yu
    -0.07
     다음과
    -0.07
     bố
    -0.07
    sar
    -0.07
     biçim
    -0.07
     CI
    -0.07
     Francis
    -0.07
    POSITIVE LOGITS
     thunk
    0.07
     unconscious
    0.06
     attacker
    0.06
    看见
    0.05
    )<<
    0.05
    ")
↵
↵
    0.05
    (){
↵
    0.05
    _frontend
    0.05
    )).↵
    0.05
    0.05
    Activations Density 0.012%

    No Known Activations