© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 62009
    Prev
    Next
    INDEX
    Explanations

    the number of times 'read' appears along with other related metrics

    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
    olin
    -0.07
     gross
    -0.06
    cheng
    -0.06
    elsing
    -0.06
    bers
    -0.06
    оÑĩ
    -0.06
    447
    -0.06
    ÑģÑĮко
    -0.06
    abet
    -0.06
    å§Ķ
    -0.05
    POSITIVE LOGITS
    Orm
    0.08
    .intValue
    0.07
    #
    0.07
    رØŃ
    0.06
    tent
    0.06
    à¥īय
    0.06
    ilinear
    0.06
    Ùģع
    0.06
    NECT
    0.06
    iju
    0.06
    Activations Density 0.000%

    No Known Activations