© 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. 118649
    Prev
    Next
    INDEX
    Explanations

    terms and references related to technical definitions

    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
    lish
    -0.07
     EINA
    -0.07
    stem
    -0.06
    stanov
    -0.06
     aks
    -0.06
     hotelu
    -0.06
    سÙħØ©
    -0.06
    adors
    -0.06
    lio
    -0.06
    beer
    -0.06
    POSITIVE LOGITS
    ÂĿ
    0.09
     itself
    0.07
     applied
    0.07
    used
    0.06
     used
    0.06
    ione
    0.06
     ë¶Ļ
    0.06
     ActionTypes
    0.06
    »
    0.06
     Pole
    0.06
    Activations Density 0.019%

    No Known Activations