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. 15-RESID-POST-AA
    6. 74520
    Prev
    Next
    INDEX
    Explanations

    Filler/preposition words

    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
     Paw
    -0.07
     Liga
    -0.07
    (PRO
    -0.06
     stag
    -0.06
     glacier
    -0.06
    Tambah
    -0.06
    셨
    -0.06
     Ст
    -0.06
     mùi
    -0.06
     met
    -0.06
    POSITIVE LOGITS
     '[
    0.06
     κ
    0.06
    *=
    0.06
     "$
    0.06
     pathlib
    0.06
    ΄
    0.06
    CALL
    0.06
    ombs
    0.06
    }.${
    0.06
    :=
    0.06
    Activations Density 0.076%

    No Known Activations