© 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. 71483
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to gene regulation and signaling pathways

    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
    ież
    -0.07
    ulace
    -0.07
    اص
    -0.07
    parcel
    -0.07
    ego
    -0.07
    erras
    -0.07
    SOLE
    -0.07
     burden
    -0.07
    igne
    -0.07
     quotient
    -0.07
    POSITIVE LOGITS
     Loose
    0.07
    627
    0.06
     loose
    0.06
    gon
    0.06
    629
    0.06
     fe
    0.06
    pes
    0.06
     bind
    0.05
    633
    0.05
     Morales
    0.05
    Activations Density 0.007%

    No Known Activations