© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3189
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional weight or impact

    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
     smart
    -0.06
     Barcl
    -0.06
    iry
    -0.06
    eson
    -0.06
    emo
    -0.06
     Kod
    -0.06
     landing
    -0.05
    cratch
    -0.05
     fancy
    -0.05
     interpre
    -0.05
    POSITIVE LOGITS
    ding
    0.08
    /goto
    0.08
    Intialized
    0.08
     gratuites
    0.07
    antly
    0.07
    -notification
    0.07
    uger
    0.07
    GuidId
    0.07
    ospace
    0.07
     we
    0.07
    Activations Density 0.003%

    No Known Activations