© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97121
    Prev
    Next
    INDEX
    Explanations

    references to television show renewals and seasons

    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
    amat
    -0.06
    zed
    -0.06
    zb
    -0.06
    undi
    -0.06
    urr
    -0.06
    edges
    -0.06
     Cheer
    -0.06
    моÑĢ
    -0.06
    lane
    -0.06
    ryn
    -0.06
    POSITIVE LOGITS
    phy
    0.08
    'gc
    0.07
    ultipart
    0.07
    PHY
    0.06
    iske
    0.06
    achment
    0.06
    erval
    0.06
    irst
    0.06
    avad
    0.06
    atch
    0.06
    Activations Density 0.040%

    No Known Activations