© 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. 94946
    Prev
    Next
    INDEX
    Explanations

    limitations or constraints of various systems or processes

    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
    PLIC
    -0.06
    acades
    -0.06
    hue
    -0.06
    znám
    -0.06
     Böylece
    -0.06
    uron
    -0.06
    ÑĢеж
    -0.06
    ilenames
    -0.05
    .erb
    -0.05
    yon
    -0.05
    POSITIVE LOGITS
     limit
    0.17
     limits
    0.17
     limitations
    0.15
     Limits
    0.15
     Limit
    0.14
    limit
    0.14
     limitation
    0.14
     limite
    0.14
    Limit
    0.13
    .limit
    0.13
    Activations Density 0.046%

    No Known Activations