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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-RESID-POST-AA
    6. 114592
    Prev
    Next
    INDEX
    Explanations

    parentheses and numbers

    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
     Datensch
    -0.07
     cf
    -0.06
    dress
    -0.06
    lemma
    -0.06
     Ih
    -0.06
    _course
    -0.06
     chan
    -0.06
     weighing
    -0.06
     klub
    -0.06
     або
    -0.06
    POSITIVE LOGITS
     Inventory
    0.07
    eced
    0.06
     Rib
    0.06
    mouth
    0.06
     Psych
    0.06
     readiness
    0.06
     birisi
    0.06
    ;margin
    0.06
    SA
    0.06
    Failed
    0.06
    Activations Density 0.035%

    No Known Activations