© 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. 61817
    Prev
    Next
    INDEX
    Explanations

    dates, particularly those referencing November 9th

    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
    ady
    -0.07
    ìĦľëĬĶ
    -0.07
    eful
    -0.06
    àµįà´
    -0.06
    GENCY
    -0.06
    ÅĻeb
    -0.06
    arp
    -0.06
    esting
    -0.06
    ollo
    -0.06
    dsl
    -0.06
    POSITIVE LOGITS
    iembre
    0.08
    embre
    0.07
    Alive
    0.07
    bia
    0.07
    bes
    0.07
    lá
    0.07
    toy
    0.07
    lerce
    0.07
    implify
    0.07
    cura
    0.07
    Activations Density 0.035%

    No Known Activations