© 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. 17171
    Prev
    Next
    INDEX
    Explanations

    references to formatting and structure in documents or code

    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
    hood
    -0.09
    ury
    -0.08
    ager
    -0.07
    house
    -0.07
    hoa
    -0.07
    erty
    -0.07
    er
    -0.06
    hod
    -0.06
    erman
    -0.06
    hardt
    -0.06
    POSITIVE LOGITS
    ting
    0.13
    ted
    0.11
    unately
    0.10
    tingham
    0.09
    td
    0.09
    tempt
    0.09
    tt
    0.09
    tement
    0.08
    dehyde
    0.08
    .googleapis
    0.08
    Activations Density 0.010%

    No Known Activations