© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-LLAMASCOPE-RES-131K
    11. 96576
    Prev
    Next
    INDEX
    Explanations

    structured programming elements and references to data paths

    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
    ãĥ«ãĤ¯
    -0.08
    jang
    -0.08
    ï½į
    -0.08
    ussen
    -0.07
    odos
    -0.07
    éģº
    -0.07
    é«ĺçŃī
    -0.07
    _COMPILE
    -0.07
    ÐĶÐļ
    -0.07
    apg
    -0.07
    POSITIVE LOGITS
     enc
    0.07
    erah
    0.06
     enrichment
    0.06
     demands
    0.06
    ceph
    0.06
     equivalent
    0.05
     interim
    0.05
    ici
    0.05
     Ash
    0.05
     al
    0.05
    Activations Density 0.013%

    No Known Activations