© 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. 646
    Prev
    Next
    INDEX
    Explanations

    references to awards and accolades in various fields

    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
    ilet
    -0.07
    atra
    -0.07
    onica
    -0.07
    inou
    -0.07
     Gems
    -0.06
    adf
    -0.06
    empo
    -0.06
    amedi
    -0.06
    ften
    -0.06
    .ov
    -0.06
    POSITIVE LOGITS
    -thumbnails
    0.07
    @nate
    0.06
     Loc
    0.06
    ATUS
    0.06
    .lazy
    0.06
    리ìĸ´
    0.06
    askell
    0.06
    ToPoint
    0.06
     Vig
    0.06
     Astro
    0.06
    Activations Density 0.017%

    No Known Activations