© 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. 9-LLAMASCOPE-RES-131K
    11. 97869
    Prev
    Next
    INDEX
    Explanations

    references to character actions and developments within a narrative context

    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
    odic
    -0.08
    ostel
    -0.07
    ñana
    -0.07
    à¹Ĥ
    -0.07
    ViewItem
    -0.07
    ritz
    -0.07
    rubu
    -0.07
    å°ıæŶ
    -0.07
    .xmlbeans
    -0.06
    olders
    -0.06
    POSITIVE LOGITS
    áºŃn
    0.06
     Globe
    0.06
    DDL
    0.06
    ilon
    0.06
    isl
    0.06
    ipe
    0.06
    iman
    0.06
    Guess
    0.06
    ipple
    0.05
    assel
    0.05
    Activations Density 0.007%

    No Known Activations