© 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. 104024
    Prev
    Next
    INDEX
    Explanations

    mentions of awards and nominations in the context of film and acting

    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
    imeline
    -0.08
    åļ
    -0.07
     desired
    -0.06
    desired
    -0.06
    oka
    -0.06
    Registers
    -0.06
    forms
    -0.06
     active
    -0.06
    ạch
    -0.06
    okens
    -0.06
    POSITIVE LOGITS
    Performance
    0.08
     Performance
    0.07
    vant
    0.07
    OSC
    0.07
    performance
    0.07
    HF
    0.07
     optarg
    0.07
     PERFORMANCE
    0.06
     performance
    0.06
     awards
    0.06
    Activations Density 0.104%

    No Known Activations