© 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. 9-LLAMASCOPE-RES-131K
    11. 95459
    Prev
    Next
    INDEX
    Explanations

    components related to server configuration and routing rules

    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
    bourg
    -0.07
    zag
    -0.06
    etin
    -0.06
    emem
    -0.06
    ebin
    -0.06
    etimes
    -0.06
    ź
    -0.06
    onas
    -0.06
    /fixtures
    -0.06
    491
    -0.06
    POSITIVE LOGITS
    tiles
    0.07
    _AUX
    0.06
     ense
    0.06
    interop
    0.06
    акÑģим
    0.06
    genic
    0.06
    ãĥ³ãĤ¯
    0.06
     ing
    0.06
    Ïĩή
    0.06
    inspace
    0.06
    Activations Density 0.001%

    No Known Activations