© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 2894
    Prev
    Next
    INDEX
    Explanations

    claims and assertions regarding events or issues

    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
    åħ¥ãĤĮ
    -0.07
    /or
    -0.06
    ire
    -0.06
    assi
    -0.06
    Ñĥда
    -0.06
    çĬ¶åĨµ
    -0.06
     éĩİ
    -0.06
    udas
    -0.06
    appe
    -0.06
    DOMNode
    -0.06
    POSITIVE LOGITS
    /assert
    0.08
     rằng
    0.07
     that
    0.07
    æŀľ
    0.06
    ants
    0.06
     bahwa
    0.06
     ignorance
    0.06
    andex
    0.06
    that
    0.06
    .SIG
    0.06
    Activations Density 0.014%

    No Known Activations