© 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. 11-RESID-POST-AA
    11. 79916
    Prev
    Next
    INDEX
    Explanations

    Abbreviations in academic papers

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    moving
    -0.07
     red
    -0.07
    iatric
    -0.07
    味
    -0.06
    fdc
    -0.06
     sugar
    -0.06
     coat
    -0.06
     lowered
    -0.06
    927
    -0.06
     segue
    -0.06
    POSITIVE LOGITS
     elkaar
    0.07
    @Bean
    0.07
    .ico
    0.06
    _ACTIVITY
    0.06
    cancellationToken
    0.06
     skyline
    0.06
     practice
    0.06
    ｉ
    0.06
     слож
    0.06
    _CON
    0.06
    Activations Density 0.077%

    No Known Activations