© 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. 104063
    Prev
    Next
    INDEX
    Explanations

    references to significant changes or transformations related to location and structure

    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
    shal
    -0.07
    chet
    -0.07
    nat
    -0.07
    afort
    -0.07
    rende
    -0.07
    antity
    -0.07
    tha
    -0.07
    rak
    -0.07
    ynet
    -0.06
    attach
    -0.06
    POSITIVE LOGITS
     process
    0.09
     happened
    0.09
     done
    0.09
     occurred
    0.08
     occurs
    0.08
     occur
    0.08
     happen
    0.08
     happens
    0.08
     happening
    0.08
     Process
    0.08
    Activations Density 0.120%

    No Known Activations