© 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 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. 61069
    Prev
    Next
    INDEX
    Explanations

    phrases that describe systematic processes or mechanisms

    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
    ulan
    -0.06
    @Resource
    -0.06
     Grass
    -0.06
    WISE
    -0.06
    jerne
    -0.06
    åĿª
    -0.06
    ARN
    -0.06
    inks
    -0.06
    enge
    -0.06
    Configurer
    -0.06
    POSITIVE LOGITS
    ayd
    0.06
    oningen
    0.06
    eld
    0.06
     Necessary
    0.06
    /includes
    0.06
     offline
    0.06
    (old
    0.06
    full
    0.06
    eldo
    0.06
     Schro
    0.06
    Activations Density 0.000%

    No Known Activations