© 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. 129564
    Prev
    Next
    INDEX
    Explanations

    phrases indicating separation or isolation from others

    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
    วม
    -0.07
     ontvangst
    -0.07
    λιο
    -0.07
     Hüs
    -0.07
    ìľĦìĽIJ
    -0.07
     Reputation
    -0.07
    ESS
    -0.07
    å±
    -0.06
    cete
    -0.06
    ãģ®æĸ¹
    -0.06
    POSITIVE LOGITS
     reality
    0.08
     except
    0.07
     normal
    0.07
     ever
    0.07
     most
    0.07
    except
    0.06
     altogether
    0.06
     influence
    0.06
     main
    0.06
     contact
    0.06
    Activations Density 0.018%

    No Known Activations