© 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. 88978
    Prev
    Next
    INDEX
    Explanations

    references to mathematical structures and conditions

    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
    ths
    -0.06
    ((-
    -0.06
     Grape
    -0.06
    asta
    -0.05
     therein
    -0.05
    akis
    -0.05
    ester
    -0.05
    ethoven
    -0.05
    id
    -0.05
     Lemon
    -0.05
    POSITIVE LOGITS
    strup
    0.08
    yre
    0.07
    PURE
    0.07
     Hart
    0.07
     bacheca
    0.07
    groupid
    0.07
    ArgumentException
    0.07
    ifact
    0.06
    ôm
    0.06
    autiful
    0.06
    Activations Density 0.027%

    No Known Activations