© 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. 85192
    Prev
    Next
    INDEX
    Explanations

    themes of unity and collective human experience

    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
    á»ijng
    -0.08
    SFML
    -0.08
    OrElse
    -0.07
    Äįky
    -0.07
    rimon
    -0.07
    formance
    -0.07
     Fell
    -0.07
     наÑĤÑĥ
    -0.07
    /Dk
    -0.07
    scopes
    -0.07
    POSITIVE LOGITS
    967
    0.07
    pras
    0.07
     merit
    0.06
     grav
    0.06
     comb
    0.06
    éĤ¦
    0.06
     Pom
    0.06
    åIJ§
    0.06
    ä¼ģ
    0.06
    llib
    0.06
    Activations Density 0.003%

    No Known Activations