© 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. 106787
    Prev
    Next
    INDEX
    Explanations

    strong references to specific organizations or institutions

    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
    i
    -0.09
    brahim
    -0.08
    ÛĮ
    -0.07
    a
    -0.07
    edom
    -0.07
    и
    -0.07
    edBy
    -0.07
     Tradable
    -0.07
    isson
    -0.07
    iÄĩ
    -0.07
    POSITIVE LOGITS
    lık
    0.08
    ogue
    0.08
    oe
    0.07
    'ın
    0.07
    ls
    0.06
    lı
    0.06
    alysis
    0.06
    -ı
    0.06
    ova
    0.06
    oy
    0.06
    Activations Density 0.039%

    No Known Activations