© 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. 17-LLAMASCOPE-RES-131K
    11. 126291
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to."

    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
    .bunifuFlatButton
    -0.07
    @js
    -0.07
    _DEFIN
    -0.06
    ÑĸÑģÑĤ
    -0.06
    ViewPager
    -0.06
    cket
    -0.06
    orks
    -0.06
    quires
    -0.06
    okud
    -0.06
    ptal
    -0.06
    POSITIVE LOGITS
    atz
    0.07
    dre
    0.06
    contri
    0.06
    arna
    0.06
     teil
    0.06
    imir
    0.06
    ॰
    0.06
    iffer
    0.06
    frag
    0.06
    _UNSIGNED
    0.06
    Activations Density 0.000%

    No Known Activations