© 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. 129062
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and brackets that indicate quotes 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
    ãĤ½ãĥ³
    -0.08
    еÑĢеÑĩ
    -0.07
    abis
    -0.06
    idon
    -0.06
    ivol
    -0.06
    \/\/
    -0.06
    son
    -0.06
    apr
    -0.06
    üzel
    -0.06
    vor
    -0.06
    POSITIVE LOGITS
    sic
    0.16
     sic
    0.13
    Leaf
    0.06
    ecko
    0.06
     Wet
    0.06
     Leaf
    0.06
    ital
    0.06
    earer
    0.06
    ownik
    0.06
     damp
    0.06
    Activations Density 0.010%

    No Known Activations