© 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. 17-LLAMASCOPE-RES-131K
    11. 74877
    Prev
    Next
    INDEX
    Explanations

    terms related to documentation and organization of information

    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
    viron
    -0.08
    eldon
    -0.08
    endar
    -0.07
    ALLERY
    -0.07
     ”↵↵
    -0.07
    ëł´
    -0.07
    (æ°´
    -0.06
    upiter
    -0.06
     Regents
    -0.06
    tribution
    -0.06
    POSITIVE LOGITS
    :↵
    0.13
    :↵↵
    0.10
     :↵
    0.10
    ï¼ļ↵
    0.09
    :č↵
    0.09
    ):↵
    0.09
    ]:↵
    0.08
    (click
    0.07
    :</
    0.07
    :");↵
    0.07
    Activations Density 0.047%

    No Known Activations