© 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. 30980
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations related to equations and variables in scientific contexts

    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
    /{}/
    -0.07
    assin
    -0.07
    -pill
    -0.06
    fsp
    -0.06
    ching
    -0.06
    axies
    -0.06
    usat
    -0.06
     tomb
    -0.06
    pill
    -0.06
    rai
    -0.06
    POSITIVE LOGITS
     =
    0.07
     ::=
    0.07
    elic
    0.07
     Goodman
    0.07
     consist
    0.06
     =↵↵
    0.06
    ħn
    0.06
    å°±æĺ¯
    0.06
    áÅĻ
    0.06
     Pek
    0.06
    Activations Density 0.210%

    No Known Activations