© 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. 17-LLAMASCOPE-RES-131K
    11. 69497
    Prev
    Next
    INDEX
    Explanations

    conjunctions indicating relationships between actions or conditions

    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
    pos
    -0.07
     Kaf
    -0.07
    iu
    -0.07
     dem
    -0.06
    erti
    -0.06
    culo
    -0.06
     prot
    -0.06
     stere
    -0.06
     Nich
    -0.06
     Ent
    -0.06
    POSITIVE LOGITS
    ysa
    0.07
    ÑĢобÑĸÑĤ
    0.07
    amenti
    0.07
    eping
    0.07
    ublic
    0.07
     consect
    0.07
    alue
    0.07
    enville
    0.06
    اصÙĦ
    0.06
     Vin
    0.06
    Activations Density 0.000%

    No Known Activations