© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 94452
    Prev
    Next
    INDEX
    Explanations

    references to book reviews and related discussions in a literary 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
    upyter
    -0.06
    оваÑĤÑĮÑģÑı
    -0.06
    BIT
    -0.06
    thin
    -0.06
     forces
    -0.06
    hn
    -0.06
    379
    -0.06
    astes
    -0.06
    ummer
    -0.05
    ÙĪاء
    -0.05
    POSITIVE LOGITS
    rech
    0.08
    ashing
    0.07
     تÙĪر
    0.07
     interview
    0.06
    afil
    0.06
     Interview
    0.06
    Interview
    0.06
    вед
    0.06
     Interviews
    0.06
    omanip
    0.06
    Activations Density 0.032%

    No Known Activations