© 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. 3-RESID-POST-AA
    11. 121767
    Prev
    Next
    INDEX
    Explanations

    u

    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
    rk
    -0.06
    绩
    -0.06
     즉
    -0.06
     sans
    -0.06
     ster
    -0.06
     (.
    -0.06
    rieben
    -0.06
    Perl
    -0.06
    isiert
    -0.05
     дли
    -0.05
    POSITIVE LOGITS
    gu
    0.23
    agu
    0.15
    igu
    0.14
    GU
    0.13
     Agu
    0.12
    igua
    0.11
    angu
    0.11
    gue
    0.10
    ingu
    0.10
    ague
    0.10
    Activations Density 0.013%

    No Known Activations