© 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. 107476
    Prev
    Next
    INDEX
    Explanations

    concepts related to support, recognition, and institutional procedures

    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
    OSP
    -0.07
    .qq
    -0.07
     rost
    -0.07
    ABCDEFGHIJKLMNOP
    -0.07
    .ir
    -0.07
    епÑĤи
    -0.07
    ÑįÑĦ
    -0.07
    ÙĪرد
    -0.07
    اØŃت
    -0.07
    rani
    -0.07
    POSITIVE LOGITS
     of
    0.08
     ang
    0.07
     rem
    0.06
    estroy
    0.06
    _of
    0.06
    /documentation
    0.05
    oenix
    0.05
    ãģŁãĤģãģ®
    0.05
    up
    0.05
    551
    0.05
    Activations Density 0.046%

    No Known Activations