© 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. 76990
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation indicating excitement or emotional expression

    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
    amping
    -0.07
    iez
    -0.06
    豪
    -0.06
    ãĥªãĥ¼
    -0.06
    boo
    -0.06
    važ
    -0.06
    ķ
    -0.06
    IMG
    -0.06
     tho
    -0.06
    orld
    -0.06
    POSITIVE LOGITS
    umbed
    0.07
    Cancelable
    0.07
    imbus
    0.06
    aye
    0.06
     nuest
    0.06
    .untracked
    0.06
     yes
    0.06
    ripper
    0.06
    allen
    0.06
    _YES
    0.06
    Activations Density 0.318%

    No Known Activations