© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 125563
    Prev
    Next
    INDEX
    Explanations

    phrases indicating companionship or association

    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
     addCriterion
    -0.07
    occer
    -0.07
    andel
    -0.07
    ¢åįķ
    -0.07
    avana
    -0.07
    educt
    -0.07
    antha
    -0.06
     è¦
    -0.06
    uada
    -0.06
    artz
    -0.06
    POSITIVE LOGITS
    bjerg
    0.07
    oro
    0.06
    QUE
    0.06
    coni
    0.06
    _serialize
    0.06
    opro
    0.06
    _resize
    0.06
     Classic
    0.06
    ston
    0.05
     Brooke
    0.05
    Activations Density 0.030%

    No Known Activations