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. 95985
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Eclipse."

    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
    oyo
    -0.08
    olis
    -0.07
    imetype
    -0.07
    avras
    -0.06
     Meredith
    -0.06
    rych
    -0.06
    lig
    -0.06
    lacak
    -0.06
    line
    -0.06
    UPPORTED
    -0.06
    POSITIVE LOGITS
    ãĥ£
    0.07
    platz
    0.07
    164
    0.06
    CAF
    0.06
    -wide
    0.06
    >true
    0.06
    walking
    0.06
    stakes
    0.06
    iever
    0.06
    cow
    0.06
    Activations Density 0.002%

    No Known Activations