© 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. 981
    Prev
    Next
    INDEX
    Explanations

    complex terms related to policies, accomplishments, and academic discussions

    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
    ishly
    -0.07
    ειο
    -0.07
    strar
    -0.07
    izable
    -0.07
    enties
    -0.07
    rian
    -0.07
    opoulos
    -0.07
    ÑĪев
    -0.06
    enstein
    -0.06
    nelle
    -0.06
    POSITIVE LOGITS
    364
    0.07
    259
    0.07
    pects
    0.07
    ography
    0.06
    ics
    0.06
    antry
    0.06
    otto
    0.06
    ars
    0.06
    eps
    0.06
     hur
    0.06
    Activations Density 0.064%

    No Known Activations