© 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. 126294
    Prev
    Next
    INDEX
    Explanations

    instances of multiline equations or expressions in mathematical contexts

    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
    enko
    -0.06
     tat
    -0.06
    adan
    -0.06
     pop
    -0.06
    pop
    -0.05
     Nah
    -0.05
    elly
    -0.05
     Pop
    -0.05
    iv
    -0.05
    [
    -0.05
    POSITIVE LOGITS
    oui
    0.10
    tors
    0.07
    Printf
    0.07
    _NT
    0.07
    _TM
    0.07
    indre
    0.07
    /stretch
    0.07
    rack
    0.07
    toi
    0.07
     defaultCenter
    0.07
    Activations Density 0.002%

    No Known Activations