© 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. 15-LLAMASCOPE-RES-131K
    11. 62448
    Prev
    Next
    INDEX
    Explanations

    phrases indicating sections or endings in documentation

    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
    olic
    -0.06
    hen
    -0.06
    ierge
    -0.06
     att
    -0.06
     augment
    -0.06
    åłĤ
    -0.06
     Settlement
    -0.06
    ht
    -0.06
    onto
    -0.06
    sters
    -0.06
    POSITIVE LOGITS
    ç¼
    0.08
    lamaz
    0.07
    Defs
    0.07
    rá
    0.07
    uges
    0.07
    uent
    0.07
    ë¬
    0.07
    ãĥ¼ãĥĨãĤ£
    0.06
    elapsed
    0.06
    .Arguments
    0.06
    Activations Density 0.003%

    No Known Activations