© 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. 15-LLAMASCOPE-RES-131K
    11. 87752
    Prev
    Next
    INDEX
    Explanations

    elements related to scholarly articles and their formatting

    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
    ãĥªãĥ³
    -0.06
    κÏģι
    -0.06
    asi
    -0.06
    ÑĤÑĢо
    -0.06
     otherwise
    -0.06
    eyse
    -0.06
    licht
    -0.06
    antis
    -0.06
    Å¡i
    -0.06
    ategorical
    -0.06
    POSITIVE LOGITS
    dera
    0.08
    indr
    0.07
    DOI
    0.07
    íķĻíļĮ
    0.07
    .ManyToMany
    0.07
    421
    0.06
    ameron
    0.06
    <p
    0.06
    gabe
    0.06
    INES
    0.06
    Activations Density 0.017%

    No Known Activations