© 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. 55779
    Prev
    Next
    INDEX
    Explanations

    characters and file-related methods and 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
    nemonic
    -0.08
    imetype
    -0.07
    ajÄħc
    -0.07
    ål
    -0.07
    byter
    -0.07
    ernetes
    -0.07
    aukee
    -0.07
    iedades
    -0.07
    rowse
    -0.07
    realm
    -0.06
    POSITIVE LOGITS
    itta
    0.07
    edo
    0.07
     Compatibility
    0.07
    stanov
    0.06
     bindActionCreators
    0.06
    _ary
    0.06
    Ïĥα
    0.06
    ìĽĶë¶ĢíĦ°
    0.06
    ered
    0.06
     compatibility
    0.06
    Activations Density 0.166%

    No Known Activations