© 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. 17-LLAMASCOPE-RES-131K
    11. 71219
    Prev
    Next
    INDEX
    Explanations

    instances of demand, accusations, and communication about legal and ethical issues

    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
    issing
    -0.10
    strand
    -0.08
    eft
    -0.08
    istle
    -0.08
    ovi
    -0.08
    á»ijng
    -0.08
    èĶµ
    -0.08
    ãģŀ
    -0.07
    zos
    -0.07
    λÏī
    -0.07
    POSITIVE LOGITS
     during
    0.07
     outside
    0.07
     a
    0.06
     twice
    0.06
     an
    0.06
     private
    0.06
     while
    0.06
     m
    0.06
     and
    0.06
    il
    0.06
    Activations Density 0.027%

    No Known Activations