© 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. 93679
    Prev
    Next
    INDEX
    Explanations

    phrases related to causation or implications

    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
    essler
    -0.08
    اÙĨÙĩ
    -0.07
    اÛĮØ´
    -0.06
    plib
    -0.06
    marks
    -0.06
    chu
    -0.06
    .Companion
    -0.06
    amy
    -0.06
    è½
    -0.06
    oret
    -0.06
    POSITIVE LOGITS
    atively
    0.08
    entially
    0.08
     rằng
    0.07
    /exp
    0.07
    OTES
    0.07
    ément
    0.07
    ively
    0.07
     that
    0.07
    že
    0.07
    urn
    0.06
    Activations Density 0.014%

    No Known Activations