© 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 EvalsExportsinterp-engineNEWAPI 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. 31138
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and concepts related to sequences and convergence

    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
    ãĥĨãĥ«
    -0.07
    ambi
    -0.06
    Refresh
    -0.06
    ustin
    -0.06
    ongoose
    -0.06
     åĸ
    -0.06
    jev
    -0.06
    _tokenize
    -0.06
    peon
    -0.06
    ombok
    -0.06
    POSITIVE LOGITS
    lim
    0.12
     lim
    0.10
     convergence
    0.10
     Lim
    0.09
     conver
    0.08
    Lim
    0.08
    inch
    0.07
    _lim
    0.07
     sequence
    0.07
     eventually
    0.07
    Activations Density 0.298%

    No Known Activations