© 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. 40764
    Prev
    Next
    INDEX
    Explanations

    numerical data and dates

    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
     becer
    -0.08
    สาร
    -0.07
     McCoy
    -0.07
    ado
    -0.07
     ÙĥÙĨد
    -0.07
    etto
    -0.07
    ÑģоÑĤ
    -0.07
     NÄĽm
    -0.07
    rello
    -0.07
    سر
    -0.07
    POSITIVE LOGITS
    akis
    0.07
     lay
    0.07
     heads
    0.06
    Ø¡
    0.05
    essel
    0.05
    801
    0.05
     Dunk
    0.05
    oline
    0.05
    #ae
    0.05
    sd
    0.05
    Activations Density 0.022%

    No Known Activations