© 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. 26906
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to optimization strategies in various 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
    oran
    -0.07
    ž
    -0.07
    abouts
    -0.07
    inated
    -0.06
    age
    -0.06
    lÃŃÄį
    -0.06
    ãĥ©ãĥ³ãĤ¹
    -0.06
    ucer
    -0.06
    orce
    -0.06
    .hadoop
    -0.06
    POSITIVE LOGITS
    /max
    0.08
    imal
    0.08
    ³
    0.08
    /min
    0.08
    abile
    0.08
    riding
    0.07
    /opt
    0.07
    åĩĨ
    0.07
     Eg
    0.07
    ALLY
    0.07
    Activations Density 0.020%

    No Known Activations