© 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. 77409
    Prev
    Next
    INDEX
    Explanations

    references to cellular structures or components involved in 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
    érique
    -0.08
    rung
    -0.08
    otron
    -0.07
    raph
    -0.07
    atori
    -0.07
    CLUDING
    -0.07
    ipc
    -0.07
    raries
    -0.07
    emens
    -0.07
    umbing
    -0.07
    POSITIVE LOGITS
    ainer
    0.08
    ech
    0.08
    ificates
    0.07
    ez
    0.07
    t
    0.07
    uche
    0.07
    909
    0.07
    sen
    0.06
    ele
    0.06
    eb
    0.06
    Activations Density 0.028%

    No Known Activations