© 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. 16373
    Prev
    Next
    INDEX
    Explanations

    phrases related to sharing content or information

    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
    stan
    -0.06
    agoon
    -0.05
     Strand
    -0.05
    hape
    -0.05
    vertis
    -0.05
    _ENCODING
    -0.05
    ibal
    -0.05
    éĽ
    -0.05
    оги
    -0.05
     ä¹
    -0.05
    POSITIVE LOGITS
     export
    0.08
    export
    0.08
    -export
    0.07
     save
    0.07
     exporting
    0.07
    prung
    0.07
    hang
    0.07
    save
    0.07
     Sends
    0.07
    /save
    0.07
    Activations Density 0.010%

    No Known Activations