© 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. 90300
    Prev
    Next
    INDEX
    Explanations

    phrases related to measurements or dimensions

    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
    redi
    -0.07
    emsp
    -0.07
    eliness
    -0.06
    ITHER
    -0.06
    rine
    -0.06
    rous
    -0.06
    earable
    -0.06
    orgia
    -0.06
    iÄĻ
    -0.06
     dispersion
    -0.06
    POSITIVE LOGITS
    zes
    0.07
    شار
    0.06
    γκÏĮ
    0.06
    ÑĢай
    0.06
     Nha
    0.06
    Ïģί
    0.06
     âĢ»
    0.06
    /goto
    0.06
     ï¼ľ
    0.06
     Typ
    0.06
    Activations Density 0.000%

    No Known Activations