© 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. 96559
    Prev
    Next
    INDEX
    Explanations

    technical terms and variable names related to programming and constraints

    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
    byn
    -0.07
    iente
    -0.07
    ientes
    -0.06
    roma
    -0.06
    ebek
    -0.06
    Ñı
    -0.06
    eos
    -0.06
    casecmp
    -0.06
    Äı
    -0.06
    356
    -0.06
    POSITIVE LOGITS
    adius
    0.07
    ëĿ¼ëıĦ
    0.06
    OnInit
    0.06
    ystack
    0.06
    rength
    0.06
    ãĥ¼ãĥĭ
    0.06
     nested
    0.06
    enticated
    0.06
    HORT
    0.06
    endon
    0.06
    Activations Density 0.055%

    No Known Activations