© 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. 28583
    Prev
    Next
    INDEX
    Explanations

    the occurrence of significant terms related to prior information or 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
    riteln
    -0.06
    çŃĨ
    -0.06
    ç²ī
    -0.06
    Ùĩر
    -0.06
    åŀ
    -0.06
    _iff
    -0.06
    adium
    -0.06
    runner
    -0.06
     pen
    -0.06
     stat
    -0.06
    POSITIVE LOGITS
    sov
    0.07
    eniable
    0.07
    alic
    0.07
    agina
    0.06
     Cord
    0.06
     Willis
    0.06
    .hs
    0.06
    emiz
    0.06
    ument
    0.06
     wiki
    0.06
    Activations Density 0.000%

    No Known Activations