© 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. 16225
    Prev
    Next
    INDEX
    Explanations

    references to stock performance metrics and travel comparisons

    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
    xae
    -0.06
     Cf
    -0.06
    rics
    -0.06
    utschen
    -0.06
    .lb
    -0.06
    uff
    -0.06
     omn
    -0.06
    sez
    -0.06
    immel
    -0.06
    ilib
    -0.06
    POSITIVE LOGITS
    /Foundation
    0.07
    PEG
    0.07
    å
    0.07
    inke
    0.07
    _fwd
    0.06
    ERO
    0.06
    /layouts
    0.06
    )new
    0.06
    istration
    0.06
    InThe
    0.06
    Activations Density 0.000%

    No Known Activations