© 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. 17-LLAMASCOPE-RES-131K
    11. 77056
    Prev
    Next
    INDEX
    Explanations

    variations of concepts or ideas expressed in multiple forms or dimensions

    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
    iven
    -0.07
    ogi
    -0.07
    axe
    -0.07
    à¥Ģà¤Ĥ
    -0.06
     affect
    -0.06
     Ease
    -0.06
    699
    -0.06
    ̧
    -0.06
    unan
    -0.06
    vip
    -0.06
    POSITIVE LOGITS
     forms
    0.14
    forms
    0.12
     Forms
    0.11
    Forms
    0.11
     varieties
    0.11
     variety
    0.10
     various
    0.09
     formas
    0.09
     variants
    0.09
     çeÅŁit
    0.09
    Activations Density 0.028%

    No Known Activations