© 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. 17-LLAMASCOPE-RES-131K
    11. 94045
    Prev
    Next
    INDEX
    Explanations

    web addresses or URLs

    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
    bjerg
    -0.08
    964
    -0.07
    aign
    -0.07
    hift
    -0.06
    apel
    -0.06
    hoe
    -0.06
    òi
    -0.06
    âce
    -0.06
    erais
    -0.06
    enthal
    -0.06
    POSITIVE LOGITS
    xmlns
    0.07
    IELDS
    0.07
    chema
    0.07
    üns
    0.07
    loub
    0.07
     decl
    0.06
     Parkway
    0.06
    DTD
    0.06
    ,www
    0.06
     xmlns
    0.06
    Activations Density 0.002%

    No Known Activations