© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 88671
    Prev
    Next
    INDEX
    Explanations

    significant nouns and corresponding phrases related to academic and intellectual topics

    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
    alse
    -0.08
    ICI
    -0.07
    arshal
    -0.07
    onders
    -0.07
     ganze
    -0.07
    attles
    -0.07
    ebek
    -0.06
     Campos
    -0.06
    ãĥ«ãĥī
    -0.06
    خصÙĪص
    -0.06
    POSITIVE LOGITS
     role
    0.10
     characteristics
    0.07
     why
    0.07
     roles
    0.07
     ways
    0.07
     reasons
    0.07
     how
    0.07
    role
    0.07
     recent
    0.07
     importance
    0.06
    Activations Density 0.032%

    No Known Activations