© 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. 76980
    Prev
    Next
    INDEX
    Explanations

    phrases signaling suggestions for education reform

    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
    Lastly
    -0.07
    iliz
    -0.07
     same
    -0.07
    ëĵ±
    -0.07
    èij
    -0.07
    ylland
    -0.07
     Lastly
    -0.07
    antan
    -0.07
    ille
    -0.07
    fter
    -0.07
    POSITIVE LOGITS
     --
    0.06
    /or
    0.06
    iser
    0.06
    ling
    0.06
    ãĥŃãĥ³
    0.05
    ging
    0.05
    366
    0.05
     pseud
    0.05
    oming
    0.05
    met
    0.05
    Activations Density 0.351%

    No Known Activations