© 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. 94246
    Prev
    Next
    INDEX
    Explanations

    references to TED Talks and videos

    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
    urf
    -0.07
    REEN
    -0.07
     akadem
    -0.07
    shall
    -0.07
     Proud
    -0.07
    यन
    -0.06
    phinx
    -0.06
    azon
    -0.06
    fos
    -0.06
     createAction
    -0.06
    POSITIVE LOGITS
     TED
    0.13
    TED
    0.09
     speech
    0.07
     speaker
    0.07
     presentation
    0.07
     talk
    0.07
     talks
    0.07
     clip
    0.07
     Hers
    0.06
     Ted
    0.06
    Activations Density 0.008%

    No Known Activations