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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90207
    Prev
    Next
    INDEX
    Explanations

    references to types of news and entertainment content

    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
    fluid
    -0.07
    -chan
    -0.07
    achuset
    -0.07
    enco
    -0.06
    etto
    -0.06
    £¨
    -0.06
     Isles
    -0.06
     türlü
    -0.06
    chl
    -0.06
    clipse
    -0.06
    POSITIVE LOGITS
    erb
    0.07
    rys
    0.07
    abox
    0.06
     Schmidt
    0.06
    IRR
    0.06
    etchup
    0.06
     dikke
    0.06
    753
    0.06
    ront
    0.06
    FML
    0.06
    Activations Density 0.028%

    No Known Activations