© 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. 78207
    Prev
    Next
    INDEX
    Explanations

    changes in service structures and community dynamics

    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
    .gwt
    -0.08
    ä¸įå¾Ĺ
    -0.07
    wich
    -0.07
    kowski
    -0.07
    दर
    -0.06
    ãĤ¤ãĥ¤
    -0.06
    lfw
    -0.06
     unlike
    -0.06
    _existing
    -0.06
    urette
    -0.06
    POSITIVE LOGITS
     more
    0.09
     ones
    0.08
    æĽ´
    0.08
     instead
    0.08
    æĽ´åĬł
    0.08
     amore
    0.08
     daha
    0.07
     Instead
    0.07
    Instead
    0.07
     emphasis
    0.07
    Activations Density 0.019%

    No Known Activations