© 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. 106984
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating end-of-sentence or transitions

    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
    ucci
    -0.07
    enberg
    -0.07
    eyer
    -0.07
    ãĥ³ãĥij
    -0.06
    é
    -0.06
    óa
    -0.06
    епÑĤи
    -0.06
    .ls
    -0.06
     Arbor
    -0.06
    áº
    -0.06
    POSITIVE LOGITS
    kaz
    0.06
     Sil
    0.06
    dsp
    0.06
    fen
    0.06
    +xml
    0.06
    vanced
    0.06
    andin
    0.06
    717
    0.06
    dB
    0.06
    ajas
    0.06
    Activations Density 0.018%

    No Known Activations