© 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. 118889
    Prev
    Next
    INDEX
    Explanations

    references to scientific inquiry and exploration

    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
    enge
    -0.09
     perman
    -0.07
    ISA
    -0.07
    /assert
    -0.07
    idor
    -0.06
    deme
    -0.06
    uhl
    -0.06
     Dodd
    -0.06
    regunta
    -0.06
    ½Ķ
    -0.06
    POSITIVE LOGITS
     freely
    0.10
    orer
    0.07
     naturally
    0.07
     natural
    0.07
     rather
    0.07
     instead
    0.07
     gradually
    0.07
     slowly
    0.07
     meanwhile
    0.06
    ValuePair
    0.06
    Activations Density 0.032%

    No Known Activations