© 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. 40662
    Prev
    Next
    INDEX
    Explanations

    technical terms and functions related to geometric calculations and data extraction

    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
    anne
    -0.08
    krom
    -0.07
    ëĬIJ
    -0.07
    nak
    -0.07
    getRow
    -0.07
    //{{
    -0.07
     tuz
    -0.06
    kinci
    -0.06
    asic
    -0.06
    _PEER
    -0.06
    POSITIVE LOGITS
    ophys
    0.07
     BUFF
    0.07
    å£
    0.06
    emo
    0.06
    oodles
    0.06
     morphology
    0.06
     Pikachu
    0.06
     Buffalo
    0.06
    oucher
    0.06
    ÑıÑħ
    0.06
    Activations Density 0.009%

    No Known Activations