© 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. 9-LLAMASCOPE-RES-131K
    11. 94892
    Prev
    Next
    INDEX
    Explanations

    phrases indicating capability or possibility for a broad audience

    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
    ibur
    -0.07
    arme
    -0.06
     all
    -0.06
     elsewhere
    -0.06
    lock
    -0.06
    .
    -0.06
     Nur
    -0.06
    essor
    -0.06
     Radius
    -0.06
     only
    -0.06
    POSITIVE LOGITS
    íĹĪ
    0.07
    ÏĦεÏģ
    0.07
    onn
    0.07
    olin
    0.07
    antt
    0.06
    orer
    0.06
    autiful
    0.06
    ause
    0.06
    igid
    0.06
    ones
    0.06
    Activations Density 0.007%

    No Known Activations