© 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. 77750
    Prev
    Next
    INDEX
    Explanations

    contractions and forms of the verb "to be" used in various contexts

    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
    uni
    -0.07
     antiqu
    -0.07
    945
    -0.06
    STAT
    -0.06
    å¾Ĺ
    -0.06
    lude
    -0.06
    isses
    -0.06
    ä¹±
    -0.06
    ouver
    -0.06
    arcy
    -0.06
    POSITIVE LOGITS
    enco
    0.09
     Ritch
    0.07
    ivet
    0.07
    akash
    0.07
    _mC
    0.07
    ãĢĤ↵↵↵↵↵↵
    0.07
    lamaz
    0.07
    LBL
    0.07
    _rq
    0.06
    GMEM
    0.06
    Activations Density 0.021%

    No Known Activations