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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96225
    Prev
    Next
    INDEX
    Explanations

    possessive forms indicating ownership or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hed
    -0.06
    inst
    -0.06
    rett
    -0.06
    backs
    -0.06
     Geile
    -0.06
    hi
    -0.06
    γη
    -0.06
    ride
    -0.06
    asts
    -0.06
    icals
    -0.06
    POSITIVE LOGITS
    abad
    0.07
    otton
    0.06
    WebService
    0.06
    ÏĨÏīν
    0.06
     either
    0.06
    ourd
    0.06
    LOY
    0.06
    udy
    0.06
    vero
    0.06
    fony
    0.06
    Activations Density 0.002%

    No Known Activations