© 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. 130410
    Prev
    Next
    INDEX
    Explanations

    references to locations or geographical contexts within the text

    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
    our
    -0.06
    070
    -0.06
    theid
    -0.06
    ائب
    -0.06
     Wright
    -0.06
    lessly
    -0.06
    çŃĭ
    -0.06
     by
    -0.06
    fold
    -0.05
    é¼
    -0.05
    POSITIVE LOGITS
    igma
    0.07
    igers
    0.07
    olley
    0.07
    rowsable
    0.07
    undra
    0.07
     обÑıз
    0.07
    egration
    0.07
    atts
    0.07
    wers
    0.06
     USA
    0.06
    Activations Density 0.022%

    No Known Activations