© 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 EvalsExportsAPI 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. 59119
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaboration and teamwork

    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
     selber
    -0.06
     Crisis
    -0.06
    agem
    -0.06
    ahoo
    -0.06
    reib
    -0.06
     agreed
    -0.06
     UNUSED
    -0.06
     Enough
    -0.06
     Nos
    -0.06
    धर
    -0.06
    POSITIVE LOGITS
     require
    0.14
     requires
    0.14
     Requires
    0.13
    requires
    0.13
     Äijòi
    0.13
    must
    0.12
    Requires
    0.12
     difficult
    0.12
    å¿ħé¡»
    0.12
     must
    0.12
    Activations Density 0.015%

    No Known Activations