© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90080
    Prev
    Next
    INDEX
    Explanations

    quotes and statements from individuals in a conversational or anecdotal context

    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
    blo
    -0.07
    ://
    -0.07
    bk
    -0.07
    ÑĦоÑĢми
    -0.07
    igure
    -0.07
    VERTISEMENT
    -0.07
     Heap
    -0.06
    RIPTION
    -0.06
    378
    -0.06
    gerald
    -0.06
    POSITIVE LOGITS
    705
    0.06
    $MESS
    0.06
    [s
    0.06
    ìĦł
    0.06
    Âľ
    0.06
    odal
    0.06
     Colt
    0.06
    ãĥ©ãĤ¤
    0.06
    antal
    0.06
    -SA
    0.06
    Activations Density 0.024%

    No Known Activations