© 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. 15-RESID-POST-AA
    11. 84805
    Prev
    Next
    INDEX
    Explanations

    reducing negative impact

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bg
    -0.07
     holes
    -0.07
    oid
    -0.07
     rend
    -0.06
    flatMap
    -0.06
    Then
    -0.06
    oma
    -0.06
    mu
    -0.06
    \admin
    -0.06
    uldu
    -0.06
    POSITIVE LOGITS
     �
    0.07
    _lazy
    0.06
     fetisch
    0.06
    iland
    0.06
    .barDockControl
    0.06
    erç
    0.06
     FileSystem
    0.06
     �
    0.06
    نتی
    0.06
     ضر
    0.06
    Activations Density 0.136%

    No Known Activations