© 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. 70194
    Prev
    Next
    INDEX
    Explanations

    file path references in code or markup

    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
    ci
    -0.07
    ãģŃ
    -0.06
    537
    -0.06
    esa
    -0.06
    yna
    -0.06
    pear
    -0.06
    owan
    -0.06
    vection
    -0.06
    iets
    -0.06
    _skb
    -0.06
    POSITIVE LOGITS
    ady
    0.07
    olid
    0.07
     Fus
    0.06
    oka
    0.06
    isiyle
    0.06
    ravel
    0.06
    .opendaylight
    0.06
    pedia
    0.06
    ninger
    0.06
     Cost
    0.06
    Activations Density 0.000%

    No Known Activations