Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96186
    Prev
    Next
    INDEX
    Explanations

    terms related to color schemes in a programming context

    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
    glob
    -0.07
    gle
    -0.07
    ë§ī
    -0.06
    bound
    -0.06
     factors
    -0.06
    ieder
    -0.06
    ´Ģ
    -0.06
     DropIndex
    -0.06
    purple
    -0.06
     einf
    -0.06
    POSITIVE LOGITS
    _lite
    0.07
    енÑģ
    0.06
    Ĥæķ°
    0.06
    oma
    0.06
    дÑĢом
    0.06
    aroo
    0.06
    akis
    0.06
    виж
    0.06
    _algo
    0.06
    ereum
    0.06
    Activations Density 0.002%

    No Known Activations