© 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. 899
    Prev
    Next
    INDEX
    Explanations

    occurrences of actions involving decision-making and interactions within a process

    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
    .scalablytyped
    -0.07
     dazu
    -0.07
    Ì
    -0.06
    nees
    -0.06
    ÅĻet
    -0.06
    lah
    -0.06
    isman
    -0.06
     Ih
    -0.06
    olet
    -0.06
     Band
    -0.06
    POSITIVE LOGITS
    ledon
    0.07
    ules
    0.07
    ifice
    0.07
     EXEMPLARY
    0.07
     or
    0.07
    æŁIJ
    0.06
    ylum
    0.06
    icer
    0.06
    onym
    0.06
     или
    0.06
    Activations Density 0.017%

    No Known Activations