© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 17-LLAMASCOPE-RES-131K
    11. 129909
    Prev
    Next
    INDEX
    Explanations

    references to bleeding and injuries related to skin or mucous membranes

    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
     demonstr
    -0.07
     ÑĤÑĢан
    -0.07
     slo
    -0.06
     Rahmen
    -0.06
    ât
    -0.06
    oom
    -0.06
     guts
    -0.06
     wom
    -0.06
    èĤ©
    -0.06
    ensis
    -0.06
    POSITIVE LOGITS
     pupil
    0.08
     pupils
    0.08
    agna
    0.07
    .scalablytyped
    0.07
     unp
    0.07
    ruba
    0.07
    é¾
    0.07
     eyes
    0.06
     PROCUREMENT
    0.06
     cracks
    0.06
    Activations Density 0.040%

    No Known Activations