© 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. 19-RESID-POST-AA
    11. 87683
    Prev
    Next
    INDEX
    Explanations

    Code/technical context

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FA
    -0.08
    Pos
    -0.07
    _proj
    -0.07
     underway
    -0.06
    Hal
    -0.06
     cx
    -0.06
    Los
    -0.06
     Bad
    -0.06
     Su
    -0.06
    -like
    -0.06
    POSITIVE LOGITS
    NSNotificationCenter
    0.08
    _folders
    0.07
     code
    0.07
    .InnerText
    0.07
     Tablet
    0.06
    Globals
    0.06
    request
    0.06
    (script
    0.06
    44
    0.06
    packageName
    0.06
    Activations Density 0.000%

    No Known Activations