© 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. 87186
    Prev
    Next
    INDEX
    Explanations

    URLs or web addresses

    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
    ansi
    -0.07
    oppers
    -0.07
    ryn
    -0.06
    abeth
    -0.06
    ãĥ¯ãĥ¼
    -0.06
    anian
    -0.06
    éĿ©
    -0.06
    VML
    -0.06
    veau
    -0.06
    onation
    -0.06
    POSITIVE LOGITS
    ighted
    0.08
    rippling
    0.06
    iro
    0.06
     kra
    0.06
     içi
    0.06
    encia
    0.06
    å¬
    0.06
    .Utc
    0.06
    .drive
    0.06
    marsh
    0.06
    Activations Density 0.001%

    No Known Activations