© 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
    7. Resid Post - 131k
    9. 27-RESID-POST-AA
    11. 104116
    Prev
    Next
    INDEX
    Explanations

    time periods

    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
     doPost
    -0.07
     gateway
    -0.07
    agn
    -0.07
     Ja
    -0.07
     success
    -0.07
    _local
    -0.07
     TOUCH
    -0.07
     sempre
    -0.07
    <|begin_of_text|>
    -0.06
    (power
    -0.06
    POSITIVE LOGITS
    erable
    0.06
    ║
    0.06
     경북
    0.06
     역시
    0.05
    ποιη
    0.05
    ()?
    0.05
    intValue
    0.05
     Rhino
    0.05
    [^
    0.05
    역시
    0.05
    Activations Density 0.027%

    No Known Activations