© 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. 29213
    Prev
    Next
    INDEX
    Explanations

    expressions of preference or admiration

    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
    icamente
    -0.09
    asaki
    -0.07
    ntl
    -0.07
    ãĥ¼ãĥ¬
    -0.07
    angelo
    -0.07
    enen
    -0.07
    gression
    -0.07
    аÑĢан
    -0.07
    ioxide
    -0.07
    andas
    -0.07
    POSITIVE LOGITS
    able
    0.09
    892
    0.07
    ably
    0.07
    ous
    0.07
    ç´ł
    0.06
     conf
    0.06
    onia
    0.06
    -minded
    0.06
    erto
    0.06
    itung
    0.06
    Activations Density 0.002%

    No Known Activations