© 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. 90314
    Prev
    Next
    INDEX
    Explanations

    keywords related to film and media

    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
    جÙĪ
    -0.06
     familiar
    -0.06
     familiarity
    -0.06
    departments
    -0.06
    242
    -0.06
    SCAN
    -0.05
    Webpack
    -0.05
     Baldwin
    -0.05
    гаÑĢ
    -0.05
    аÑĢан
    -0.05
    POSITIVE LOGITS
    imits
    0.08
    oldemort
    0.07
     SpringApplication
    0.07
    clr
    0.07
    aves
    0.07
    utsch
    0.07
    Äįen
    0.07
    ADDE
    0.06
    ayscale
    0.06
     schön
    0.06
    Activations Density 0.002%

    No Known Activations