© 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. 17694
    Prev
    Next
    INDEX
    Explanations

    citations and references in academic writing

    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
    ubern
    -0.07
    YPRE
    -0.06
    ngrx
    -0.06
    .scalablytyped
    -0.06
    ocene
    -0.06
    ColumnsMode
    -0.06
     diligence
    -0.06
    rug
    -0.06
    gré
    -0.06
    anship
    -0.06
    POSITIVE LOGITS
    éĻ¶
    0.06
    brates
    0.06
    elpers
    0.06
    apes
    0.06
     #%
    0.06
    @Id
    0.06
     ^↵
    0.06
    ÑģÑĤоÑĢ
    0.06
     Athena
    0.06
    èģ
    0.06
    Activations Density 0.005%

    No Known Activations