© 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. 56731
    Prev
    Next
    INDEX
    Explanations

    phrases indicating positive evaluations or impressions of performances

    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
     eskort
    -0.08
    ’e
    -0.08
     ostat
    -0.08
     StÅĻed
    -0.07
    otime
    -0.07
    aphore
    -0.07
    Ь
    -0.07
    lıģını
    -0.07
    opensource
    -0.07
     оÑģÑĤаннÑĸ
    -0.07
    POSITIVE LOGITS
     a
    0.16
     an
    0.14
     lots
    0.10
    ability
    0.09
    a
    0.09
    ä¸Ģç§į
    0.08
     ability
    0.08
     eine
    0.08
     some
    0.08
     increased
    0.08
    Activations Density 0.070%

    No Known Activations