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

    Neuronpedia

    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. 17-LLAMASCOPE-RES-131K
    11. 105747
    Prev
    Next
    INDEX
    Explanations

    programming and technical terminology related to memory management and operations

    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
    ifen
    -0.07
    acent
    -0.07
    aż
    -0.07
    isse
    -0.07
     Brno
    -0.07
    adiens
    -0.07
    ivet
    -0.07
    avern
    -0.06
    umbs
    -0.06
     Bren
    -0.06
    POSITIVE LOGITS
    ukan
    0.07
     distributed
    0.07
     gram
    0.07
     Fernandez
    0.06
     Gram
    0.06
    inalg
    0.06
    inka
    0.06
    dense
    0.06
     per
    0.06
     prov
    0.06
    Activations Density 0.004%

    No Known Activations