© 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. 74990
    Prev
    Next
    INDEX
    Explanations

    terms related to historical records and references

    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
    Enlarge
    -0.06
    akan
    -0.06
    icast
    -0.06
    chs
    -0.06
    innen
    -0.06
    eton
    -0.06
     NR
    -0.06
    ÑģÑĤва
    -0.06
    rels
    -0.06
    amax
    -0.06
    POSITIVE LOGITS
     recorded
    0.09
     dates
    0.07
     date
    0.07
     dated
    0.07
     appearance
    0.07
    -record
    0.07
     باÙĤ
    0.07
     mention
    0.07
    bare
    0.07
    record
    0.06
    Activations Density 0.013%

    No Known Activations