© 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. 15-LLAMASCOPE-RES-131K
    11. 87370
    Prev
    Next
    INDEX
    Explanations

    notable achievements and contributions in various fields

    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
    ãĥŃãĥ³
    -0.06
    oran
    -0.06
    ita
    -0.06
    Ñħи
    -0.06
    862
    -0.06
    portion
    -0.05
    .dtd
    -0.05
    ichen
    -0.05
    /Home
    -0.05
    /inet
    -0.05
    POSITIVE LOGITS
    IMS
    0.07
    IDO
    0.07
     recent
    0.07
    pom
    0.06
    anka
    0.06
    èĻ«
    0.06
    raki
    0.06
    erb
    0.06
    Repeated
    0.06
    idia
    0.06
    Activations Density 0.015%

    No Known Activations