© 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. 55738
    Prev
    Next
    INDEX
    Explanations

    important historical events or milestones

    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
    iese
    -0.06
    ogle
    -0.06
    iba
    -0.06
    ignum
    -0.06
     latter
    -0.06
     #__
    -0.06
     McCabe
    -0.06
    ":"'
    -0.06
    Msp
    -0.06
    raft
    -0.06
    POSITIVE LOGITS
    neau
    0.07
    0.07
    sonian
    0.07
    .Abstractions
    0.07
    lick
    0.06
    onet
    0.06
     background
    0.06
     Brill
    0.06
    Background
    0.06
    prech
    0.06
    Activations Density 0.005%

    No Known Activations