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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90289
    Prev
    Next
    INDEX
    Explanations

    terms related to copyright and ownership of creative work

    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
    zung
    -0.08
    preter
    -0.07
    evi
    -0.07
    éĥ
    -0.06
     Pé
    -0.06
    ment
    -0.06
    uyo
    -0.06
    aring
    -0.06
    thumbs
    -0.06
    wiki
    -0.06
    POSITIVE LOGITS
     Personal
    0.07
    ochen
    0.06
    ãĥ¼ãĥĵ
    0.06
     æĵ
    0.06
    anagan
    0.06
     personal
    0.06
    _nat
    0.06
    rompt
    0.06
    aland
    0.06
    éłħ
    0.06
    Activations Density 0.006%

    No Known Activations