© 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. 28939
    Prev
    Next
    INDEX
    Explanations

    instances of view counts related to media or content exposure

    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
     Bene
    -0.07
    lint
    -0.06
    attle
    -0.06
    ouis
    -0.06
    iken
    -0.06
     Dam
    -0.06
    ive
    -0.06
    ummer
    -0.06
    iej
    -0.06
    trib
    -0.06
    POSITIVE LOGITS
    obe
    0.07
    ाà¤ĩ
    0.06
    éIJĺ
    0.06
    ัà¸ģà¸Ķ
    0.06
     fitte
    0.06
    enderit
    0.06
    endcode
    0.06
    yre
    0.06
    lander
    0.06
    PIO
    0.06
    Activations Density 0.004%

    No Known Activations