© 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. 59671
    Prev
    Next
    INDEX
    Explanations

    references to puzzle-solving and marketing strategies

    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
    ALER
    -0.07
    ROTO
    -0.07
    AWS
    -0.07
    elsen
    -0.06
     stereotypes
    -0.06
     cong
    -0.06
    ections
    -0.06
    .Compute
    -0.06
    uchos
    -0.06
    ptions
    -0.06
    POSITIVE LOGITS
     campaign
    0.07
    ugo
    0.07
    omin
    0.06
     máºŃt
    0.06
     website
    0.06
     Nylon
    0.06
    campaign
    0.06
    imei
    0.06
    issent
    0.06
    führ
    0.06
    Activations Density 0.005%

    No Known Activations