© 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. 17-LLAMASCOPE-RES-131K
    11. 116786
    Prev
    Next
    INDEX
    Explanations

    mentions of the city of Berlin

    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
    eyJ
    -0.07
    oret
    -0.07
    axe
    -0.07
    anchor
    -0.07
    arel
    -0.07
    servers
    -0.07
    s
    -0.06
    érica
    -0.06
    estic
    -0.06
    elder
    -0.06
    POSITIVE LOGITS
    беÑĢ
    0.07
     ÐijеÑĢ
    0.07
     Ber
    0.07
    zeug
    0.07
    ium
    0.07
    etta
    0.07
    stem
    0.06
    bers
    0.06
     DC
    0.06
    haps
    0.06
    Activations Density 0.004%

    No Known Activations