© 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. 15195
    Prev
    Next
    INDEX
    Explanations

    information related to contributions and collaborations from diverse authors or groups

    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
    atron
    -0.08
    @student
    -0.07
     Ãľlke
    -0.07
     CONSTANTS
    -0.07
    ẩu
    -0.07
    ppe
    -0.07
    inae
    -0.07
    ekil
    -0.07
    afen
    -0.07
    holm
    -0.07
    POSITIVE LOGITS
     ranging
    0.15
     varying
    0.13
     diverse
    0.12
     either
    0.11
     varied
    0.11
     ranged
    0.11
     mostly
    0.10
     various
    0.10
     range
    0.10
    either
    0.09
    Activations Density 0.051%

    No Known Activations