© 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. 72375
    Prev
    Next
    INDEX
    Explanations

    terms related to technical specifications and measurements in processes

    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
    acher
    -0.08
    BuilderInterface
    -0.08
    .TabStop
    -0.07
    оÑĢд
    -0.06
    ksen
    -0.06
    oola
    -0.06
    atten
    -0.06
    propTypes
    -0.06
    posium
    -0.06
    @student
    -0.06
    POSITIVE LOGITS
     dabei
    0.06
     dafür
    0.06
     COMMENTS
    0.05
    ê¹Įì§Ģ
    0.05
     thereof
    0.05
    839
    0.05
    ÃŃny
    0.05
     Ocak
    0.05
    apos
    0.05
    eton
    0.05
    Activations Density 0.074%

    No Known Activations