© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 98103
    Prev
    Next
    INDEX
    Explanations

    references to responsibilities and duties assigned to individuals or groups

    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
    aire
    -0.08
    ussen
    -0.07
    amera
    -0.07
    VOKE
    -0.07
    147
    -0.07
    _GRE
    -0.07
    ambre
    -0.06
    355
    -0.06
    anan
    -0.06
     detriment
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.08
     dis
    0.07
     task
    0.07
     tasks
    0.06
    enny
    0.06
    /lic
    0.06
    ServletResponse
    0.06
     Task
    0.06
    edii
    0.06
    htdocs
    0.06
    Activations Density 0.007%

    No Known Activations