© 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. 93502
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the act of rising or increasing in position or status

    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
    íĨµ
    -0.07
    .Raycast
    -0.07
    igner
    -0.07
    insk
    -0.07
     bystand
    -0.06
    ominator
    -0.06
     />'
    -0.06
    éIJ
    -0.06
    ecess
    -0.06
    ªĮ
    -0.06
    POSITIVE LOGITS
     up
    0.09
    avel
    0.07
    ivi
    0.07
    546
    0.07
     Gri
    0.06
    706
    0.06
    wind
    0.06
    zel
    0.06
    bra
    0.06
    656
    0.06
    Activations Density 0.017%

    No Known Activations