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. 77117
    Prev
    Next
    INDEX
    Explanations

    references to tumors and related biological processes

    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
    enton
    -0.07
    uttle
    -0.07
    eur
    -0.07
    enna
    -0.07
    erner
    -0.07
    sword
    -0.07
    enko
    -0.06
    ноÑģÑı
    -0.06
    en
    -0.06
    -speaking
    -0.06
    POSITIVE LOGITS
    ous
    0.07
     size
    0.07
    oids
    0.07
    UGIN
    0.07
    ieten
    0.07
    avigation
    0.07
     growth
    0.07
    /host
    0.07
    lettes
    0.07
     cells
    0.06
    Activations Density 0.004%

    No Known Activations