© 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. 42325
    Prev
    Next
    INDEX
    Explanations

    terms related to ebooks and digital reading materials

    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
     tapes
    -0.08
    år
    -0.07
     Brew
    -0.06
    å½¹
    -0.06
     Hlav
    -0.06
     tape
    -0.06
    adera
    -0.06
    reesome
    -0.06
    anger
    -0.06
     maid
    -0.06
    POSITIVE LOGITS
    /print
    0.08
    pii
    0.08
    머ëĭĪ
    0.08
    PLAIN
    0.08
    /mobile
    0.08
    ï¸
    0.08
    ombs
    0.07
    ems
    0.07
    /video
    0.07
    /Web
    0.07
    Activations Density 0.004%

    No Known Activations