© 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. 39292
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitional phrases that indicate contrast or exception

    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
     vs
    -0.06
    jud
    -0.06
    isco
    -0.05
    vs
    -0.05
     linear
    -0.05
    fore
    -0.05
    sent
    -0.05
    linear
    -0.05
    rang
    -0.05
     g
    -0.05
    POSITIVE LOGITS
     actually
    0.13
    actually
    0.11
     Actually
    0.11
    Actually
    0.10
     aslında
    0.09
    åħ¶å®ŀ
    0.08
    abr
    0.07
    ¶ģ
    0.07
    nock
    0.07
     ÑĦакÑĤи
    0.07
    Activations Density 0.025%

    No Known Activations