© 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. 92895
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the existence or presence of something

    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
    orea
    -0.07
    ãģĹãĤĩ
    -0.06
     سخ
    -0.06
    ลล
    -0.06
    umer
    -0.06
    .camel
    -0.06
    .fore
    -0.06
     vez
    -0.06
    ameleon
    -0.06
    æĤī
    -0.06
    POSITIVE LOGITS
    ein
    0.07
     third
    0.07
     somebody
    0.06
     someone
    0.06
    swer
    0.06
    _pod
    0.06
    cta
    0.06
     other
    0.06
     somewhere
    0.06
     explanation
    0.06
    Activations Density 0.032%

    No Known Activations