© 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. 15-LLAMASCOPE-RES-131K
    11. 104346
    Prev
    Next
    INDEX
    Explanations

    references to the functionality and usability of various objects or concepts

    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
    iaux
    -0.07
    jsc
    -0.06
    bette
    -0.06
    jez
    -0.06
    olf
    -0.06
    Æ°Æ¡ng
    -0.06
    osu
    -0.06
     complet
    -0.06
    bose
    -0.06
    ầy
    -0.06
    POSITIVE LOGITS
    çĶ¨äºİ
    0.09
     unchanged
    0.08
     use
    0.08
    Used
    0.07
     Used
    0.07
     used
    0.07
    enin
    0.07
    -use
    0.07
    used
    0.07
    _used
    0.07
    Activations Density 0.069%

    No Known Activations