© 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 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. 29065
    Prev
    Next
    INDEX
    Explanations

    instances of the word "for."

    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
    ı
    -0.07
    _ASSUME
    -0.07
    .yang
    -0.07
    HeaderCode
    -0.06
    quo
    -0.06
    /Typography
    -0.06
    zcze
    -0.06
     Genius
    -0.06
    gency
    -0.06
     dequeueReusableCellWithIdentifier
    -0.06
    POSITIVE LOGITS
     build
    0.07
    onet
    0.07
    azel
    0.07
    ylon
    0.07
    義
    0.06
    à¹Ģà¸Ĺ
    0.06
    DOT
    0.06
     нав
    0.06
    заб
    0.06
    oden
    0.06
    Activations Density 0.000%

    No Known Activations