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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 119344
    Prev
    Next
    INDEX
    Explanations

    monetary values and financial contributions

    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
    ccione
    -0.07
    ensex
    -0.07
    åķª
    -0.07
    enever
    -0.07
    åħ¨åĽ½
    -0.07
    inker
    -0.07
     NATIONAL
    -0.07
    AXB
    -0.07
    ÏĦικα
    -0.07
    иком
    -0.07
    POSITIVE LOGITS
    US
    0.07
    USD
    0.07
    itu
    0.06
    -US
    0.06
    itus
    0.06
    ius
    0.06
     US
    0.06
    inton
    0.06
    frica
    0.06
    lus
    0.06
    Activations Density 0.031%

    No Known Activations