© 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. 73158
    Prev
    Next
    INDEX
    Explanations

    technical terms related to healthcare and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text segments that appear immediately after a document beginning marker, often representing the initial content of a new article, post, or document.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     aforementioned
    -0.10
    ,but
    -0.09
    ,and
    -0.09
    (and
    -0.09
    ,in
    -0.09
     btw
    -0.08
     IMO
    -0.08
     afore
    -0.07
    ,on
    -0.07
    :↵
    -0.07
    POSITIVE LOGITS
    "urls
    0.08
     STDCALL
    0.08
    'gc
    0.08
    .bunifuFlatButton
    0.07
     RuntimeObject
    0.07
    :UIAlert
    0.07
    tuk
    0.07
     RuntimeMethod
    0.07
     iddi
    0.07
    plode
    0.07
    Activations Density 71.128%

    No Known Activations