© 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. 22-LLAMASCOPE-RES-131K
    11. 4144
    Prev
    Next
    INDEX
    Explanations

    references to new beginnings or initiations, particularly in the context of performances or releases

    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
    apsed
    -0.08
    sian
    -0.07
    ách
    -0.07
    éĻµ
    -0.07
    seed
    -0.07
    adem
    -0.07
    stell
    -0.07
    yal
    -0.07
    umb
    -0.07
    abee
    -0.07
    POSITIVE LOGITS
    ante
    0.13
    antes
    0.11
    ANTE
    0.09
    ductory
    0.09
    antly
    0.08
    bing
    0.08
     appearance
    0.08
    appearance
    0.07
    ant
    0.07
    /original
    0.07
    Activations Density 0.007%

    No Known Activations