© 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. 106536
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate methods or means to achieve something

    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
    angelo
    -0.07
    lek
    -0.07
    gram
    -0.07
    áj
    -0.07
    pedo
    -0.07
    ated
    -0.07
    atern
    -0.07
    him
    -0.07
    ordin
    -0.07
    itag
    -0.07
    POSITIVE LOGITS
    urement
    0.10
    owment
    0.07
    ród
    0.07
    orem
    0.06
    isters
    0.06
    ings
    0.06
    pir
    0.06
    ìłĢ
    0.06
    ãĢħ
    0.06
    .fm
    0.06
    Activations Density 0.011%

    No Known Activations