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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 27-RESID-POST-AA
    6. 10224
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _CALLBACK
    -0.07
     động
    -0.06
    /title
    -0.06
     itir
    -0.06
    ใจ
    -0.06
    _prefs
    -0.06
     vitamin
    -0.06
    ?",
    -0.06
    ictionaries
    -0.06
    .length
    -0.06
    POSITIVE LOGITS
     Namespace
    0.07
     Gotham
    0.07
    ymology
    0.07
     Роз
    0.06
    :NS
    0.06
     �
    0.06
     stag
    0.06
     poke
    0.06
    (Seq
    0.06
    Opp
    0.06
    Activations Density 0.014%

    No Known Activations