© 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. 76278
    Prev
    Next
    INDEX
    Explanations

    references to ease or difficulty in understanding concepts and their initial appearances versus deeper meanings

    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
    aceous
    -0.07
    heit
    -0.06
     unnamed
    -0.06
    ceae
    -0.06
    cia
    -0.06
    olet
    -0.06
    722
    -0.06
     unidentified
    -0.06
     ~~
    -0.06
     incor
    -0.05
    POSITIVE LOGITS
     seeming
    0.23
     seemingly
    0.21
     seem
    0.18
     seemed
    0.17
     seems
    0.17
     appear
    0.15
     Seems
    0.15
     каж
    0.14
     appears
    0.14
     appearing
    0.13
    Activations Density 0.150%

    No Known Activations