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

    Neuronpedia

    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. 56889
    Prev
    Next
    INDEX
    Explanations

    phrases indicating evidence of capability or reliability

    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
    aura
    -0.08
     Gew
    -0.07
    _pb
    -0.07
    ugo
    -0.07
    iveau
    -0.07
    veau
    -0.07
    avn
    -0.06
    iland
    -0.06
    ervo
    -0.06
    arga
    -0.06
    POSITIVE LOGITS
     ability
    0.08
     repeatedly
    0.08
    peated
    0.07
     prove
    0.07
     proven
    0.07
     capacity
    0.07
    ÙĦات
    0.07
     Alt
    0.06
     proved
    0.06
     willingness
    0.06
    Activations Density 0.017%

    No Known Activations