© 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. 125775
    Prev
    Next
    INDEX
    Explanations

    phrases that convey incongruity or a mismatch in context

    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
    lider
    -0.07
    cin
    -0.07
    icari
    -0.06
    ebo
    -0.06
    asier
    -0.06
    coins
    -0.06
    âce
    -0.06
    icontrol
    -0.06
    ares
    -0.06
    WO
    -0.06
    POSITIVE LOGITS
    fit
    0.09
     presence
    0.09
     Presence
    0.08
     fit
    0.08
     intrusion
    0.08
    presence
    0.08
    Mismatch
    0.08
    Presence
    0.07
     Fit
    0.07
     inappropriate
    0.07
    Activations Density 0.059%

    No Known Activations