© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 93601
    Prev
    Next
    INDEX
    Explanations

    formatted timestamps and file extensions

    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
    ichni
    -0.08
    Ùī
    -0.07
    811
    -0.07
    ittest
    -0.06
    elan
    -0.06
    etty
    -0.06
    bie
    -0.06
     ramp
    -0.06
    çĵ¦
    -0.06
     tack
    -0.06
    POSITIVE LOGITS
    veis
    0.06
     paci
    0.06
    duk
    0.06
     Bones
    0.06
    iers
    0.06
    ëijĺ
    0.06
    ulta
    0.06
    resi
    0.06
    ¹
    0.05
     Pot
    0.05
    Activations Density 0.000%

    No Known Activations