© 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. 82964
    Prev
    Next
    INDEX
    Explanations

    possessive constructions indicating ownership or connection

    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
    SSERT
    -0.07
    addon
    -0.07
     hoch
    -0.06
    sek
    -0.06
    ssc
    -0.06
    /loose
    -0.06
    ARAM
    -0.06
     _{}
    -0.06
    /or
    -0.06
    ÑģÑĤÑİ
    -0.06
    POSITIVE LOGITS
     own
    0.13
     oneself
    0.12
     Own
    0.10
    Own
    0.09
    own
    0.09
     OWN
    0.08
    -self
    0.08
    unda
    0.08
     próp
    0.07
    erus
    0.07
    Activations Density 0.006%

    No Known Activations