© 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. 3866
    Prev
    Next
    INDEX
    Explanations

    discussions about debut films and novels, focusing on their introductions and significance

    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
    ilty
    -0.07
     pÅĻib
    -0.07
    /icon
    -0.07
    \Active
    -0.07
     Affero
    -0.07
    ila
    -0.07
    480
    -0.06
    ÑģÑıÑĤ
    -0.06
    instrument
    -0.06
    ulos
    -0.06
    POSITIVE LOGITS
     debut
    0.18
     début
    0.12
     rookie
    0.10
     maiden
    0.10
     sophomore
    0.09
     inaugural
    0.09
     isFirst
    0.08
     debuted
    0.08
     Rookie
    0.08
     Entry
    0.07
    Activations Density 0.023%

    No Known Activations