© 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. 23-RESID-POST-AA
    11. 105045
    Prev
    Next
    INDEX
    Explanations

    say "em" words

    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
     Negro
    -0.07
     STORY
    -0.06
    واهد
    -0.06
    vero
    -0.06
    pecific
    -0.06
    amina
    -0.06
    Parallel
    -0.05
     clever
    -0.05
    -to
    -0.05
    (){}↵
    -0.05
    POSITIVE LOGITS
     lips
    0.07
     yiy
    0.07
     Urs
    0.07
     depiction
    0.07
    buquerque
    0.06
    _clock
    0.06
    <UnityEngine
    0.06
     ре
    0.06
    TECT
    0.06
    专业
    0.06
    Activations Density 0.002%

    No Known Activations