© 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. 56285
    Prev
    Next
    INDEX
    Explanations

    inquiries and requests for 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
    gee
    -0.07
    bens
    -0.07
    asses
    -0.07
    zon
    -0.07
    da
    -0.07
    unto
    -0.06
     citas
    -0.06
    apo
    -0.06
    deen
    -0.06
    à¹īà¸ĩ
    -0.06
    POSITIVE LOGITS
     disc
    0.06
    dül
    0.06
    cek
    0.06
    meni
    0.06
     concept
    0.06
    ecut
    0.06
    779
    0.06
     Tell
    0.06
     how
    0.05
     sac
    0.05
    Activations Density 0.007%

    No Known Activations