© 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. 5-LLAMASCOPE-RES-131K
    11. 125422
    Prev
    Next
    INDEX
    Explanations

    the word "Recent" in various contexts

    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
     dolu
    -0.08
    amina
    -0.08
     vÃŃde
    -0.07
    à¤¾à¤ľà¤¸
    -0.07
    iei
    -0.07
    adians
    -0.07
    irut
    -0.07
    ocs
    -0.07
    uetype
    -0.07
    elman
    -0.07
    POSITIVE LOGITS
    zi
    0.07
    est
    0.06
     Papa
    0.06
    ignum
    0.06
    -made
    0.05
     wr
    0.05
    ya
    0.05
    a
    0.05
     Patterson
    0.05
    isi
    0.05
    Activations Density 0.005%

    No Known Activations