© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 28686
    Prev
    Next
    INDEX
    Explanations

    programming and mathematical terminologies related to vector operations

    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
    èį
    -0.07
     Ekon
    -0.06
     defence
    -0.06
    erule
    -0.06
    eln
    -0.06
    chal
    -0.06
    دÙĪد
    -0.06
    593
    -0.06
    одав
    -0.06
    ç´Ģ
    -0.06
    POSITIVE LOGITS
    akens
    0.07
     Rig
    0.07
     LOD
    0.07
    ãĥªãĥ³ãĤ°
    0.06
     lighting
    0.06
     THREE
    0.06
     compt
    0.06
     Phong
    0.06
    ako
    0.06
    jde
    0.06
    Activations Density 0.045%

    No Known Activations