© 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. 87590
    Prev
    Next
    INDEX
    Explanations

    references to shopping and personal attributes

    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
    ektor
    -0.08
    arbeit
    -0.07
    å
    -0.07
     Dynasty
    -0.07
    è±
    -0.06
    奴
    -0.06
    amarin
    -0.06
     åĺ
    -0.06
     Isis
    -0.06
    ãĤ¤ãĥ¤
    -0.06
    POSITIVE LOGITS
    λÏī
    0.07
    ivar
    0.07
    :frame
    0.06
    loff
    0.06
    openhagen
    0.06
    essim
    0.06
     ALOG
    0.06
     hero
    0.06
    urb
    0.06
    thers
    0.06
    Activations Density 0.007%

    No Known Activations