© 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 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. 76481
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific concepts and relationships

    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
     Constant
    -0.06
     u
    -0.06
     Spect
    -0.06
    agal
    -0.06
    _verbose
    -0.06
     reverse
    -0.06
     yield
    -0.06
     Strict
    -0.06
    apos
    -0.06
     further
    -0.06
    POSITIVE LOGITS
    WithMany
    0.08
     TCHAR
    0.08
    zcze
    0.08
    TabPage
    0.07
    ensibly
    0.07
    /MPL
    0.07
     nonatomic
    0.07
    kin
    0.07
    ça
    0.07
    ças
    0.07
    Activations Density 0.032%

    No Known Activations