© 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. 15-RESID-POST-AA
    11. 28137
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    _priv
    -0.08
    狀
    -0.07
     får
    -0.07
    OfSize
    -0.07
     semaphore
    -0.06
     Fir
    -0.06
    _two
    -0.06
    .Minimum
    -0.06
    Bern
    -0.06
     surrender
    -0.06
    POSITIVE LOGITS
    还
    0.08
    //!
    0.07
    (jLabel
    0.06
    就
    0.06
    ("(
    0.06
    양
    0.06
     distinguishing
    0.06
    (ix
    0.06
     interpretations
    0.06
    [root
    0.06
    Activations Density 0.006%

    No Known Activations