© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 130877
    Prev
    Next
    INDEX
    Explanations

    conditional phrases indicating specific circumstances or situations

    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
    agnostics
    -0.08
    isia
    -0.07
    pag
    -0.07
    ãĥ³ãĤ°
    -0.07
     меÑĩ
    -0.07
    bilt
    -0.07
     anc
    -0.07
    _codegen
    -0.07
    okud
    -0.06
    ÅĻez
    -0.06
    POSITIVE LOGITS
     compared
    0.07
     viewed
    0.07
     care
    0.06
     starting
    0.06
     both
    0.06
     unlike
    0.06
    iene
    0.06
    ãģ¡ãĤĥ
    0.06
    ien
    0.06
    üm
    0.06
    Activations Density 0.039%

    No Known Activations