© 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. 57278
    Prev
    Next
    INDEX
    Explanations

    conditional phrases that express alternatives or possibilities

    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
    सल
    -0.07
    _IA
    -0.07
    removeAttr
    -0.06
    edium
    -0.06
    vale
    -0.06
    illin
    -0.06
    íĨ¡
    -0.06
     Medium
    -0.06
    leared
    -0.06
    rieb
    -0.06
    POSITIVE LOGITS
    ivals
    0.07
    avs
    0.06
    ample
    0.06
     dispatch
    0.06
    .fits
    0.06
     indeed
    0.06
    ips
    0.06
    zenia
    0.06
    LayoutConstraint
    0.06
    itz
    0.06
    Activations Density 0.001%

    No Known Activations