© 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. 5365
    Prev
    Next
    INDEX
    Explanations

    technical coding references and file 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
    ink
    -0.06
    perm
    -0.06
    âĢ¦↵
    -0.06
    kem
    -0.06
    ya
    -0.06
    grab
    -0.06
    inking
    -0.05
    icle
    -0.05
    asks
    -0.05
    adder
    -0.05
    POSITIVE LOGITS
     explanation
    0.09
     explains
    0.08
     explaining
    0.08
    ÅĻes
    0.08
     explain
    0.08
     expl
    0.08
     explanations
    0.07
    ãĥĮ
    0.07
     explained
    0.07
    uitka
    0.07
    Activations Density 0.000%

    No Known Activations