© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83268
    Prev
    Next
    INDEX
    Explanations

    expressions of indifference or lack of concern

    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
    ysi
    -0.07
     Decomp
    -0.06
    earch
    -0.06
     Peel
    -0.06
    ocus
    -0.06
    arsers
    -0.06
    ights
    -0.06
     latch
    -0.06
    legate
    -0.06
     franca
    -0.06
    POSITIVE LOGITS
     cares
    0.14
     care
    0.14
     caring
    0.13
     cared
    0.12
     concern
    0.11
     Concern
    0.11
     Care
    0.10
    care
    0.10
    Care
    0.10
     interest
    0.09
    Activations Density 0.030%

    No Known Activations