© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 129978
    Prev
    Next
    INDEX
    Explanations

    terms related to computer systems and their functionalities

    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
    ISM
    -0.07
    antry
    -0.07
    asser
    -0.06
    à¸Ĺาà¸ĩà¸ģาร
    -0.06
    _firestore
    -0.06
    chner
    -0.06
    ocio
    -0.06
    ocs
    -0.06
     bob
    -0.06
    ugi
    -0.06
    POSITIVE LOGITS
    wide
    0.10
    atik
    0.09
    onen
    0.09
    -wide
    0.08
    UnderTest
    0.08
    atic
    0.08
    argar
    0.07
    Endian
    0.07
    atical
    0.07
    atics
    0.07
    Activations Density 0.019%

    No Known Activations