© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127883
    Prev
    Next
    INDEX
    Explanations

    references to purpose or intention 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
    sher
    -0.07
    lord
    -0.07
    abus
    -0.07
    lu
    -0.06
    hang
    -0.06
    side
    -0.06
    387
    -0.06
    \Events
    -0.06
    ãĥ¡ãĥ©
    -0.06
    ernity
    -0.06
    POSITIVE LOGITS
    -built
    0.07
    ahlen
    0.07
    bred
    0.07
    bjerg
    0.07
    fully
    0.07
    letal
    0.07
    idth
    0.07
    ansom
    0.07
    inally
    0.07
     purpose
    0.06
    Activations Density 0.004%

    No Known Activations