© 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. 61276
    Prev
    Next
    INDEX
    Explanations

    references to the LINQ library in programming contexts

    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
    jective
    -0.06
    gress
    -0.06
    ine
    -0.06
    acy
    -0.06
    تÙģ
    -0.06
    ud
    -0.06
    azen
    -0.06
     Pearl
    -0.06
    aston
    -0.06
    uide
    -0.06
    POSITIVE LOGITS
    owitz
    0.08
    crest
    0.08
    ackbar
    0.07
    дап
    0.07
    åijĬ
    0.07
    .jpa
    0.07
    ãĥĨãĥ«
    0.07
    èŃľ
    0.07
    GMT
    0.07
    .rl
    0.07
    Activations Density 0.000%

    No Known Activations