© 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. 31082
    Prev
    Next
    INDEX
    Explanations

    transitional phrases and expressions of opinion

    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
    arat
    -0.07
     Bernstein
    -0.07
    owski
    -0.07
    433
    -0.06
    lement
    -0.06
    å§ĵ
    -0.06
    -Requested
    -0.06
     Upper
    -0.06
    eyen
    -0.06
    ey
    -0.06
    POSITIVE LOGITS
     dig
    0.16
    dig
    0.13
     rant
    0.12
     Dig
    0.10
     tangent
    0.10
    rant
    0.10
     ram
    0.10
    Dig
    0.10
     topic
    0.09
     bab
    0.09
    Activations Density 0.044%

    No Known Activations