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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 30864
    Prev
    Next
    INDEX
    Explanations

    instances of reports or formal announcements

    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
    hib
    -0.07
    suming
    -0.07
    aval
    -0.07
    lemn
    -0.06
    udeau
    -0.06
    ouncements
    -0.06
    osg
    -0.06
    aptors
    -0.06
    okable
    -0.06
    lemetry
    -0.06
    POSITIVE LOGITS
     an
    0.09
     a
    0.09
     several
    0.08
    an
    0.07
     sebuah
    0.07
    312
    0.07
     two
    0.06
     ë³´ë©´
    0.06
    lu
    0.06
     Preston
    0.06
    Activations Density 0.036%

    No Known Activations