© 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. 86836
    Prev
    Next
    INDEX
    Explanations

    numerical references and citation formats in academic writing

    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
    iam
    -0.06
    igua
    -0.06
    /-
    -0.06
    gang
    -0.05
    amo
    -0.05
     characteristic
    -0.05
    ÑģÑĥ
    -0.05
     عÙħÙĪÙħÛĮ
    -0.05
    943
    -0.05
    ÙģاÙĤ
    -0.05
    POSITIVE LOGITS
    jez
    0.08
    jec
    0.08
    edo
    0.08
    inue
    0.08
    allo
    0.07
    stru
    0.07
    PIO
    0.07
    orro
    0.07
     ogs
    0.07
    sonian
    0.07
    Activations Density 0.001%

    No Known Activations