© 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. 118973
    Prev
    Next
    INDEX
    Explanations

    negative responses or denials

    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
    bew
    -0.08
    ernen
    -0.08
    imin
    -0.07
    loy
    -0.07
     versa
    -0.07
    nech
    -0.07
    άνÏĦα
    -0.07
    едж
    -0.07
    mma
    -0.07
    landa
    -0.07
    POSITIVE LOGITS
    pe
    0.09
    onen
    0.07
    ope
    0.07
     particular
    0.07
    xious
    0.06
    ises
    0.06
    isy
    0.06
     sir
    0.06
     matter
    0.06
     WAY
    0.06
    Activations Density 0.009%

    No Known Activations