© 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. 15-RESID-POST-AA
    11. 115272
    Prev
    Next
    INDEX
    Explanations

    Event dates and times

    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
    nten
    -0.07
    ýš
    -0.06
     twilight
    -0.06
    ulty
    -0.06
    führ
    -0.06
    _prov
    -0.06
     Drama
    -0.06
     рыб
    -0.06
    gm
    -0.06
     infected
    -0.06
    POSITIVE LOGITS
     uncon
    0.06
     zwarte
    0.06
     už
    0.06
     classmates
    0.06
    OUTH
    0.06
    ("-
    0.06
    Law
    0.06
     aph
    0.06
    uiltin
    0.06
    _secondary
    0.06
    Activations Density 0.011%

    No Known Activations