© 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. 56274
    Prev
    Next
    INDEX
    Explanations

    terms associated with optimization and permanence in systems

    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
    üss
    -0.06
    loo
    -0.06
    inke
    -0.06
    _MACRO
    -0.06
    Lite
    -0.06
    ixo
    -0.06
     "
    -0.06
    ernes
    -0.06
    /we
    -0.06
    /he
    -0.06
    POSITIVE LOGITS
    isms
    0.07
    ities
    0.07
    olia
    0.07
    reed
    0.07
    ism
    0.07
    739
    0.07
    igi
    0.06
     ValueEventListener
    0.06
    acades
    0.06
    isdiction
    0.06
    Activations Density 0.053%

    No Known Activations