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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RESID-POST-AA
    6. 84555
    Prev
    Next
    INDEX
    Explanations

    (*

    np_max-act · gemini-2.0-flash

    This neuron detects crystallographic data quality thresholds, in particular the intensity cutoff notation “I > 2 σ(I)”.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    χό
    -0.06
     орган
    -0.06
    �
    -0.06
     -.
    -0.06
     ấm
    -0.06
    ZERO
    -0.06
    Opened
    -0.06
     цель
    -0.06
    Leon
    -0.06
    ีข
    -0.06
    POSITIVE LOGITS
     truck
    0.07
     College
    0.07
     je
    0.07
    (img
    0.07
     Historical
    0.07
    ؟
    0.07
    odule
    0.07
    Sets
    0.07
     colleges
    0.07
    /manual
    0.06
    Activations Density 0.000%

    No Known Activations