© 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. 17-LLAMASCOPE-RES-131K
    11. 84789
    Prev
    Next
    INDEX
    Explanations

    phrases and structures related to data mapping and web source references

    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
     Ga
    -0.07
     inauguration
    -0.07
    imeline
    -0.06
    StrictEqual
    -0.06
    itsu
    -0.06
    tar
    -0.06
    965
    -0.06
    義
    -0.06
    _swap
    -0.06
    .Mutable
    -0.06
    POSITIVE LOGITS
    ints
    0.07
    _backward
    0.07
    ibt
    0.07
    ryptography
    0.07
    Kansas
    0.06
    atoria
    0.06
     Ole
    0.06
    lov
    0.06
     SQL
    0.06
    Globals
    0.06
    Activations Density 0.001%

    No Known Activations