© 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. 56468
    Prev
    Next
    INDEX
    Explanations

    references to various types of storage media and their properties

    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
    czy
    -0.07
    ģ
    -0.06
    /an
    -0.06
    atre
    -0.06
     Misc
    -0.06
     pop
    -0.06
    edy
    -0.06
     hold
    -0.06
    que
    -0.05
     reign
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.08
    omanip
    0.08
    ruz
    0.08
    IFF
    0.07
    itar
    0.07
     RESERVED
    0.07
    LAR
    0.07
    GINE
    0.07
    zburg
    0.07
    ATAL
    0.07
    Activations Density 0.003%

    No Known Activations