© 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. 23-RESID-POST-AA
    11. 105134
    Prev
    Next
    INDEX
    Explanations

    Museums

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fauc
    -0.07
    ườn
    -0.06
    contentType
    -0.06
    действ
    -0.06
     �
    -0.06
    Mus
    -0.06
    (reason
    -0.06
    imeType
    -0.06
    주소
    -0.06
    ühr
    -0.06
    POSITIVE LOGITS
    _marker
    0.07
    140
    0.07
    ้าส
    0.07
    _GRAPH
    0.06
    150
    0.06
    Χ
    0.06
    Trap
    0.06
    те
    0.06
     nicely
    0.06
     crystals
    0.06
    Activations Density 0.009%

    No Known Activations