© 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. 128227
    Prev
    Next
    INDEX
    Explanations

    references to bars and dining establishments

    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
    коÑĤ
    -0.07
    oust
    -0.07
    loor
    -0.07
    оÑģÑĥд
    -0.07
    ezi
    -0.06
    ryn
    -0.06
    nila
    -0.06
    ãĤĵãģ©
    -0.06
    .animations
    -0.06
    amed
    -0.06
    POSITIVE LOGITS
    į°
    0.08
    bers
    0.08
    /bar
    0.07
    ãĥ
    0.07
     kits
    0.07
     kit
    0.07
    à¥įह
    0.06
    .tables
    0.06
     æ¤
    0.06
    MARY
    0.06
    Activations Density 0.000%

    No Known Activations