© 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 EvalsExportsinterp-engineNEWAPI 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. 41791
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "into" in relation to various contexts

    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
    اÙĨت
    -0.08
    INCLUDED
    -0.07
    ophy
    -0.07
     еÑģÑĤе
    -0.07
    ouz
    -0.07
    kola
    -0.07
    antan
    -0.06
     Jer
    -0.06
    iem
    -0.06
    را
    -0.06
    POSITIVE LOGITS
    onz
    0.06
    135
    0.06
    /runtime
    0.06
    226
    0.06
    ewolf
    0.05
     affair
    0.05
    //{{
    0.05
    ugas
    0.05
     reign
    0.05
    epend
    0.05
    Activations Density 0.008%

    No Known Activations