© 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. 70312
    Prev
    Next
    INDEX
    Explanations

    assertions regarding the accuracy and completeness of information

    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
    urch
    -0.06
    urre
    -0.06
     dara
    -0.06
     Marks
    -0.05
    alue
    -0.05
     Prime
    -0.05
    748
    -0.05
    çĶ²
    -0.05
    MinMax
    -0.05
    éĽĦ
    -0.05
    POSITIVE LOGITS
    ızı
    0.08
    ardu
    0.07
    pac
    0.07
    Âĥ
    0.07
    ãĥ¼ãĥĨ
    0.07
    pis
    0.07
    fos
    0.07
    indre
    0.07
    ossip
    0.07
     ¦
    0.07
    Activations Density 0.004%

    No Known Activations