© 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. 71148
    Prev
    Next
    INDEX
    Explanations

    references to subjectivity and narrative in history

    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
    onet
    -0.08
    (disposing
    -0.07
    æķ¦
    -0.07
     Doe
    -0.07
    icast
    -0.06
     Cylinder
    -0.06
    éĤ¦
    -0.06
    zek
    -0.06
     Coil
    -0.06
    ograf
    -0.06
    POSITIVE LOGITS
     webs
    0.06
     filtered
    0.06
    ErrorHandler
    0.06
    å¦
    0.06
     interpretation
    0.06
    TEL
    0.06
     reality
    0.06
     depend
    0.06
    ewe
    0.06
    interpret
    0.06
    Activations Density 0.021%

    No Known Activations