Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 122929
    Prev
    Next
    INDEX
    Explanations

    version

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    保护
    -0.07
     дея
    -0.06
    (relative
    -0.06
    کش
    -0.06
    protect
    -0.06
     nhiều
    -0.06
     Доб
    -0.06
     spectro
    -0.06
     opat
    -0.06
     taxonomy
    -0.05
    POSITIVE LOGITS
     version
    0.16
    Version
    0.13
     versions
    0.13
    _version
    0.11
     Version
    0.11
    version
    0.11
     getVersion
    0.11
    -version
    0.11
    .version
    0.10
    _VERSION
    0.10
    Activations Density 0.033%

    No Known Activations