© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-LLAMASCOPE-RES-131K
    11. 95383
    Prev
    Next
    INDEX
    Explanations

    references to cryptographic integrity

    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
    adt
    -0.06
    /Area
    -0.06
    Domains
    -0.06
    ±
    -0.06
    .nd
    -0.06
    ÑĢаÑģÑĤа
    -0.06
     McM
    -0.06
    ürn
    -0.06
    iT
    -0.06
    reck
    -0.06
    POSITIVE LOGITS
    mars
    0.07
    ys
    0.07
     Morrow
    0.06
     ÑģÑħод
    0.06
    phalt
    0.06
    outu
    0.06
    endas
    0.06
    ibar
    0.06
     Rubin
    0.06
     Mint
    0.06
    Activations Density 0.000%

    No Known Activations