© 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. 15-LLAMASCOPE-RES-131K
    6. 26445
    Prev
    Next
    INDEX
    Explanations

    evaluations of enjoyment and quality in media content

    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
     literally
    -0.08
    æĮĻ
    -0.07
    à¥įà¤
    -0.07
     any
    -0.07
     permanent
    -0.06
     Liter
    -0.06
     Seriously
    -0.06
    Seriously
    -0.06
     Mathematic
    -0.06
    _literal
    -0.06
    POSITIVE LOGITS
     overall
    0.10
     although
    0.10
     nhưng
    0.09
    overall
    0.08
     but
    0.08
    ìľ¼ëĤĺ
    0.08
    although
    0.08
     BUT
    0.08
    but
    0.08
     decent
    0.07
    Activations Density 0.079%

    No Known Activations