© 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. 127445
    Prev
    Next
    INDEX
    Explanations

    terms related to matching mechanisms or functions

    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
    ated
    -0.07
    isi
    -0.07
    isl
    -0.07
    ties
    -0.07
    theless
    -0.07
    hue
    -0.07
    ates
    -0.07
    isset
    -0.06
    han
    -0.06
    /manage
    -0.06
    POSITIVE LOGITS
    (es
    0.14
    able
    0.11
    ingly
    0.10
    ings
    0.09
    yro
    0.09
    ãĥ§
    0.09
    tures
    0.08
    backs
    0.08
    maker
    0.08
    up
    0.08
    Activations Density 0.023%

    No Known Activations