© 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. 5-LLAMASCOPE-RES-131K
    11. 125935
    Prev
    Next
    INDEX
    Explanations

    content related to high-profile events or personalities

    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
    ente
    -0.07
    iferay
    -0.07
    itz
    -0.07
    alem
    -0.06
    ogen
    -0.06
    urch
    -0.06
    chaft
    -0.06
    еÑĢÑĪ
    -0.06
    oller
    -0.06
    board
    -0.06
    POSITIVE LOGITS
    'gc
    0.07
    amam
    0.07
    ¤¤
    0.07
     ++↵
    0.06
     rip
    0.06
    пÑĢа
    0.06
    ÛĮرÛĮ
    0.06
    hm
    0.06
    mÃŃt
    0.06
     rac
    0.06
    Activations Density 0.014%

    No Known Activations