© 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. 54692
    Prev
    Next
    INDEX
    Explanations

    expressions of outreach and connection to diverse communities

    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
    γÏĩ
    -0.07
    prak
    -0.06
    ily
    -0.06
    ELY
    -0.06
    quette
    -0.06
    ะ
    -0.06
    arian
    -0.06
    INTR
    -0.06
    offee
    -0.06
    हन
    -0.06
    POSITIVE LOGITS
    reach
    0.09
    ibern
    0.09
     Tent
    0.08
     reach
    0.07
     tent
    0.07
    åıĭ
    0.07
    Reach
    0.07
    หา
    0.07
    ToOne
    0.07
    imestep
    0.07
    Activations Density 0.004%

    No Known Activations