© 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. 17-LLAMASCOPE-RES-131K
    6. 127865
    Prev
    Next
    INDEX
    Explanations

    positive sentiments and evaluations about experiences or services

    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
    eri
    -0.06
     IsValid
    -0.06
    ิà¸ļ
    -0.06
    еÑı
    -0.06
    vere
    -0.06
    ilian
    -0.06
    ãĤº
    -0.06
     Platt
    -0.06
    -Mobile
    -0.06
    arranty
    -0.06
    POSITIVE LOGITS
     perfect
    0.08
    perfect
    0.08
    åł
    0.07
     win
    0.07
     plus
    0.07
     ticks
    0.07
    KEN
    0.07
    plus
    0.07
     Perfect
    0.06
     Plus
    0.06
    Activations Density 0.032%

    No Known Activations