© 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. 42002
    Prev
    Next
    INDEX
    Explanations

    references to specific numerical or statistical 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
    ichten
    -0.07
    ạc
    -0.07
    ntl
    -0.07
    urette
    -0.06
    istes
    -0.06
    ï¿
    -0.06
    _usec
    -0.06
    ertiary
    -0.06
    adors
    -0.06
     dedim
    -0.06
    POSITIVE LOGITS
     tens
    0.07
    et
    0.06
    804
    0.06
    akest
    0.06
    GenericType
    0.06
    omatic
    0.06
    ë§Į
    0.06
    elerin
    0.06
     inform
    0.06
    alf
    0.06
    Activations Density 0.001%

    No Known Activations