© 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. 125870
    Prev
    Next
    INDEX
    Explanations

    references to specific titles and related terms in the context of literature or media

    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
    γÏĮ
    -0.06
    raq
    -0.06
    ãĥ³ãĤ¬
    -0.06
    çİī
    -0.06
     Dagger
    -0.06
    ãĥ¼ãĥģ
    -0.06
    ardown
    -0.06
    ÑĢана
    -0.06
     buflen
    -0.06
    erea
    -0.06
    POSITIVE LOGITS
     law
    0.07
     Ged
    0.07
     police
    0.07
     cat
    0.07
     death
    0.07
     chilled
    0.07
     ruling
    0.07
    istrovstvÃŃ
    0.07
    ếu
    0.07
     world
    0.06
    Activations Density 0.001%

    No Known Activations