© 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. 117877
    Prev
    Next
    INDEX
    Explanations

    proper nouns and organizational names

    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
    ì©
    -0.06
    ErrorHandler
    -0.05
    leur
    -0.05
    loth
    -0.05
    ãİ
    -0.05
    ALER
    -0.05
    _SAN
    -0.05
    ongsTo
    -0.05
    Configurer
    -0.05
    /controllers
    -0.05
    POSITIVE LOGITS
     participate
    0.08
    ÑĦÑĦ
    0.07
    gio
    0.07
     оÑĩеÑĢед
    0.07
     contribution
    0.07
    otos
    0.07
    iscal
    0.07
    ierung
    0.07
     participated
    0.07
    incinn
    0.07
    Activations Density 0.014%

    No Known Activations