© 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. 22-LLAMASCOPE-RES-131K
    11. 4134
    Prev
    Next
    INDEX
    Explanations

    occurrences of the initials "JK."

    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
    ovit
    -0.08
    alim
    -0.07
    asje
    -0.07
    ROTO
    -0.07
    /INFO
    -0.07
    oÄį
    -0.07
    ellung
    -0.07
     aliqua
    -0.07
    hoc
    -0.07
    éŃ
    -0.07
    POSITIVE LOGITS
     Rowling
    0.09
    avin
    0.06
    SN
    0.06
     Rowe
    0.05
    owl
    0.05
    bs
    0.05
    .Row
    0.05
     Snape
    0.05
    emos
    0.05
    ect
    0.05
    Activations Density 0.003%

    No Known Activations