© 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. 103834
    Prev
    Next
    INDEX
    Explanations

    references to agreements and contract performance issues

    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
    chia
    -0.08
    roma
    -0.07
    awi
    -0.07
    áu
    -0.07
    assis
    -0.07
    ourt
    -0.06
    _Impl
    -0.06
    lder
    -0.06
    asis
    -0.06
    ouse
    -0.06
    POSITIVE LOGITS
     ultimate
    0.06
    IENT
    0.06
    ÙĪدÙĩ
    0.06
    ultimate
    0.06
     whirl
    0.06
    wh
    0.06
    ients
    0.06
    falls
    0.05
     sophisticated
    0.05
    ÃŃsto
    0.05
    Activations Density 0.008%

    No Known Activations