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. 95989
    Prev
    Next
    INDEX
    Explanations

    references to award winners and awards given in sports

    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
    stderr
    -0.07
    fid
    -0.07
    oner
    -0.06
    ekli
    -0.06
    277
    -0.06
    orges
    -0.06
    ú
    -0.06
    Std
    -0.06
    amil
    -0.06
    uder
    -0.06
    POSITIVE LOGITS
    linky
    0.07
    uib
    0.07
    usher
    0.06
    indre
    0.06
    cente
    0.06
     Gren
    0.06
    ови
    0.06
    .addListener
    0.06
     cent
    0.06
    loh
    0.06
    Activations Density 0.019%

    No Known Activations