© 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. 119040
    Prev
    Next
    INDEX
    Explanations

    negations or phrases indicating an absence or exception

    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
    stell
    -0.08
    ارش
    -0.07
    ixon
    -0.07
    RESS
    -0.07
    ÚĺÛĮ
    -0.07
     Vital
    -0.07
     IPs
    -0.07
    isman
    -0.07
    OrNull
    -0.07
    ÅŁehir
    -0.07
    POSITIVE LOGITS
     originally
    0.08
     Originally
    0.07
    origin
    0.07
     until
    0.07
     initially
    0.06
    Originally
    0.06
     inherited
    0.06
    ıydı
    0.06
    Cho
    0.06
     original
    0.06
    Activations Density 0.026%

    No Known Activations