© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 15676
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    kins
    -0.06
    ould
    -0.06
    atu
    -0.06
    bove
    -0.06
    GLOBALS
    -0.06
    @js
    -0.06
     personals
    -0.06
    LANG
    -0.06
     wag
    -0.06
     ç·
    -0.06
    POSITIVE LOGITS
    peg
    0.07
    èIJ¥
    0.06
    ape
    0.06
    embr
    0.06
    çĥ
    0.06
     Fritz
    0.06
    uce
    0.06
    idae
    0.06
    vrier
    0.06
     arb
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.