© 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. 15-LLAMASCOPE-RES-131K
    11. 26986
    Prev
    Next
    INDEX
    Explanations

    conjunctions that indicate contrast or exceptions

    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
    enor
    -0.08
    orem
    -0.07
    ÑģÑĮ
    -0.07
    aland
    -0.07
    itÃł
    -0.07
    ptune
    -0.07
    asma
    -0.07
    etrofit
    -0.07
    cube
    -0.07
    ilen
    -0.07
    POSITIVE LOGITS
    ting
    0.07
     Bam
    0.06
     rel
    0.06
     certain
    0.06
     sal
    0.06
    elden
    0.06
    \/\/
    0.06
     standard
    0.06
    s
    0.06
     cert
    0.06
    Activations Density 0.002%

    No Known Activations