© 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. 117490
    Prev
    Next
    INDEX
    Explanations

    references to "a" before nouns or adjectives

    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
    WithMany
    -0.07
     Premi
    -0.07
    ocol
    -0.07
    yte
    -0.07
    .Ticks
    -0.07
     доÑģ
    -0.06
    ãģĹãģ¦ãĤĭ
    -0.06
    ä¿Ĺ
    -0.06
    esta
    -0.06
    ovel
    -0.06
    POSITIVE LOGITS
    essor
    0.07
    lope
    0.06
     series
    0.06
     variety
    0.06
    arton
    0.06
    åŀĭ
    0.06
    etsy
    0.06
    undy
    0.06
     Spy
    0.06
     few
    0.06
    Activations Density 0.046%

    No Known Activations