© 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. 128491
    Prev
    Next
    INDEX
    Explanations

    phrases indicating recommendations or requirements

    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
     çŁ³
    -0.06
    ndl
    -0.06
    Ñģол
    -0.06
    ij
    -0.06
     fa
    -0.06
    itta
    -0.05
    öy
    -0.05
     even
    -0.05
    orc
    -0.05
    oji
    -0.05
    POSITIVE LOGITS
    optional
    0.10
     optional
    0.09
     Optional
    0.09
    recommended
    0.09
    Optional
    0.08
     voluntary
    0.08
    (optional
    0.08
    	Optional
    0.08
     Advantage
    0.08
     жел
    0.08
    Activations Density 0.025%

    No Known Activations