© 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. 15-LLAMASCOPE-RES-131K
    11. 88391
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and variables used 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
    ħn
    -0.07
    &E
    -0.06
    ulg
    -0.06
    elah
    -0.06
    ocol
    -0.06
    δεÏĤ
    -0.06
     getArguments
    -0.06
    ضÙĦ
    -0.06
    éĴ
    -0.06
    ulia
    -0.06
    POSITIVE LOGITS
    /gcc
    0.07
    uzzi
    0.06
    /sbin
    0.06
    344
    0.06
    iii
    0.05
     Ellison
    0.05
    bcrypt
    0.05
    atrix
    0.05
    ï
    0.05
    Callable
    0.05
    Activations Density 0.008%

    No Known Activations