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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3191
    Prev
    Next
    INDEX
    Explanations

    references to specific data, reports, or structured content in a document

    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
     unl
    -0.06
     Tanner
    -0.06
    lot
    -0.06
    нг
    -0.06
    .yy
    -0.06
    ofile
    -0.06
     Fuse
    -0.05
    kB
    -0.05
    edition
    -0.05
     Fox
    -0.05
    POSITIVE LOGITS
    imson
    0.07
     tran
    0.07
    ASURE
    0.06
    Strict
    0.06
     dedi
    0.06
    enan
    0.06
    Spy
    0.06
    _lineno
    0.06
    ENTIAL
    0.06
    eration
    0.06
    Activations Density 0.061%

    No Known Activations