© 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. 27824
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "one" and other variations indicating singularity or individuality

    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
    ENCY
    -0.07
    uta
    -0.07
    digit
    -0.06
     Vs
    -0.06
    dx
    -0.06
    -vs
    -0.06
    otron
    -0.06
    olumn
    -0.06
    .scalablytyped
    -0.06
    .bp
    -0.06
    POSITIVE LOGITS
     problem
    0.06
     Realt
    0.06
     reality
    0.06
    Ïģά
    0.06
    iens
    0.06
    ppe
    0.06
    vem
    0.06
     Pru
    0.06
    SM
    0.05
     Ach
    0.05
    Activations Density 0.023%

    No Known Activations