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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16283
    Prev
    Next
    INDEX
    Explanations

    references to historical events or legal acts related to governance and social issues

    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
    ccione
    -0.07
    istra
    -0.07
    ansa
    -0.06
     Tem
    -0.06
     Sector
    -0.06
    enders
    -0.06
    ÑģÑıÑĤ
    -0.06
     World
    -0.06
     former
    -0.06
    éĥ
    -0.06
    POSITIVE LOGITS
    British
    0.07
    иÑĩа
    0.06
    Venue
    0.06
     Innoc
    0.06
     Draco
    0.06
     stap
    0.06
     taxes
    0.06
    176
    0.06
    еÑī
    0.06
    æ®ĸ
    0.06
    Activations Density 0.002%

    No Known Activations