© 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 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. 82956
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize exclusivity or uniqueness in terms of location or availability

    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
    วย
    -0.07
    baru
    -0.07
    iaz
    -0.07
    inke
    -0.06
    trand
    -0.06
    ilton
    -0.06
    ulton
    -0.06
    esson
    -0.06
    ameleon
    -0.06
    dik
    -0.06
    POSITIVE LOGITS
     anywhere
    0.12
     elsewhere
    0.10
     except
    0.09
    à¹ĥà¸Ķ
    0.08
     nor
    0.08
    except
    0.08
     anymore
    0.07
     aside
    0.07
     кÑĢоме
    0.07
     nowhere
    0.07
    Activations Density 0.006%

    No Known Activations