© 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. 56327
    Prev
    Next
    INDEX
    Explanations

    documents that pertain to services and travel-related 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
    ãĥ¼ãĥ¬
    -0.07
    ulfilled
    -0.07
    Spr
    -0.07
    966
    -0.07
    ov
    -0.07
    سر
    -0.06
    iet
    -0.06
     Dra
    -0.06
    lettes
    -0.06
    ones
    -0.06
    POSITIVE LOGITS
    rada
    0.07
    리ìķĦ
    0.07
     Miz
    0.07
    ifter
    0.06
    na
    0.06
    над
    0.06
    osu
    0.06
     undes
    0.06
    rn
    0.06
    "display
    0.06
    Activations Density 0.158%

    No Known Activations