© 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 EvalsExportsAPI 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. 16484
    Prev
    Next
    INDEX
    Explanations

    references to various "model" types, particularly in contexts related to design or functionality

    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
    parcel
    -0.07
     Morton
    -0.06
    esi
    -0.06
    ter
    -0.06
    olver
    -0.06
    erty
    -0.06
    shire
    -0.06
    assage
    -0.06
    ansi
    -0.06
    úÄįast
    -0.06
    POSITIVE LOGITS
    led
    0.11
     getModel
    0.10
    .Model
    0.09
    =model
    0.08
    ogue
    0.08
    .mdl
    0.08
    les
    0.08
    ë§ģ
    0.08
    ledon
    0.08
    (model
    0.07
    Activations Density 0.015%

    No Known Activations