© 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. 29489
    Prev
    Next
    INDEX
    Explanations

    items and opportunities related to hiring and staff placement

    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
    INVAL
    -0.08
     Nová
    -0.07
    ILON
    -0.07
    PLIER
    -0.07
    ously
    -0.07
    bero
    -0.07
    Å¡Å¥
    -0.07
    andel
    -0.07
    _construct
    -0.07
    omba
    -0.07
    POSITIVE LOGITS
     partner
    0.10
     partners
    0.10
     funding
    0.10
     Funding
    0.09
     fund
    0.08
     suitable
    0.08
     sponsor
    0.07
     locations
    0.07
     target
    0.07
     location
    0.07
    Activations Density 0.027%

    No Known Activations