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

    Neuronpedia

    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. 105753
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "have."

    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
     toll
    -0.07
    uma
    -0.07
    Ĥæķ°
    -0.07
    ipar
    -0.07
    нима
    -0.06
    ows
    -0.06
    odiac
    -0.06
    ÙĪÙĨØ©
    -0.06
    dae
    -0.06
    ory
    -0.06
    POSITIVE LOGITS
    érer
    0.07
     mieux
    0.07
    .bc
    0.06
    eron
    0.06
    raction
    0.06
    expo
    0.06
    æŶéĹ´
    0.06
    äºĭ
    0.06
     sÃłng
    0.06
    .tt
    0.06
    Activations Density 0.024%

    No Known Activations