© 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. 3886
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming and software development

    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
    _ASSUME
    -0.08
    anford
    -0.08
     eskort
    -0.07
    omor
    -0.07
    .ssl
    -0.07
    aba
    -0.07
    .adv
    -0.07
    ocio
    -0.07
    ForRow
    -0.07
    .timedelta
    -0.07
    POSITIVE LOGITS
     namespace
    0.08
     Ali
    0.07
     ali
    0.07
     alias
    0.07
    _alias
    0.07
     Alien
    0.07
    SION
    0.06
     aliases
    0.06
    Ali
    0.06
     aliens
    0.06
    Activations Density 0.011%

    No Known Activations