© 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. 56787
    Prev
    Next
    INDEX
    Explanations

    pricing information related to events or activities

    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
    usto
    -0.07
    uard
    -0.06
    roach
    -0.06
    aket
    -0.06
    ropp
    -0.06
    amy
    -0.06
    æĭ³
    -0.06
     Fog
    -0.06
    ender
    -0.06
     aspects
    -0.06
    POSITIVE LOGITS
    imir
    0.07
    akedown
    0.07
    entry
    0.06
    ,void
    0.06
    æ¯
    0.06
    ANDARD
    0.06
     Bakan
    0.06
    âĢ³
    0.06
    áb
    0.06
    rena
    0.06
    Activations Density 0.007%

    No Known Activations