© 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. 120396
    Prev
    Next
    INDEX
    Explanations

    phrases that express anticipation or excitement about upcoming events

    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
    _FM
    -0.07
     Shine
    -0.07
    shine
    -0.07
    utin
    -0.06
    igham
    -0.06
    ãĤĤãģªãģĦ
    -0.06
    thur
    -0.06
    меÑĤÑĮ
    -0.06
    -y
    -0.06
    769
    -0.06
    POSITIVE LOGITS
     goose
    0.07
    ket
    0.07
     eye
    0.07
     ear
    0.07
    gid
    0.07
    mes
    0.07
    адж
    0.06
    jaw
    0.06
    recht
    0.06
     rival
    0.06
    Activations Density 0.117%

    No Known Activations