© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 57177
    Prev
    Next
    INDEX
    Explanations

    numerical information related to measurements or dimensions

    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
    aldo
    -0.06
    outu
    -0.06
    ifax
    -0.06
    olla
    -0.06
    uez
    -0.06
    ulen
    -0.06
    ngx
    -0.05
     Lincoln
    -0.05
    usat
    -0.05
     Jennings
    -0.05
    POSITIVE LOGITS
    سÙĪØ¨
    0.07
    åĴ²
    0.07
    TemplateName
    0.07
    igators
    0.06
    ạp
    0.06
    ENTION
    0.06
    SearchTree
    0.06
    PointerException
    0.06
    uras
    0.06
    "crypto
    0.06
    Activations Density 0.002%

    No Known Activations