© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 129844
    Prev
    Next
    INDEX
    Explanations

    academic or journal reference information

    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
     carrying
    -0.07
     carried
    -0.06
     carry
    -0.06
    UA
    -0.06
    eler
    -0.06
    consult
    -0.06
    èŃľ
    -0.06
    _CALC
    -0.06
    emi
    -0.06
    /features
    -0.05
    POSITIVE LOGITS
     proceedings
    0.10
     conference
    0.10
     attendee
    0.09
     Proceedings
    0.09
    /session
    0.09
    Conference
    0.09
     Conference
    0.08
     attendees
    0.08
    Proceed
    0.08
     proceeding
    0.08
    Activations Density 0.027%

    No Known Activations