© 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. 15-LLAMASCOPE-RES-131K
    11. 61788
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and market relationships

    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
    .gov
    -0.06
    tele
    -0.06
    oldem
    -0.06
    orda
    -0.06
     telecom
    -0.06
     cris
    -0.06
    -inc
    -0.06
    908
    -0.05
     tele
    -0.05
    _DEFINE
    -0.05
    POSITIVE LOGITS
     cancelButtonTitle
    0.07
    odel
    0.07
     ÙģرÙĪ
    0.07
    kte
    0.07
    onical
    0.06
    ÙħاÙĨ
    0.06
    annie
    0.06
    __,↵
    0.06
    CJK
    0.06
    ÄĻd
    0.06
    Activations Density 0.008%

    No Known Activations