© 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. 22-LLAMASCOPE-RES-131K
    11. 4069
    Prev
    Next
    INDEX
    Explanations

    technical terms related to signal processing and functions

    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
     norge
    -0.12
    >manual
    -0.10
     omas
    -0.09
    \Mapping
    -0.09
     danmark
    -0.09
    iscard
    -0.09
    imagenes
    -0.09
    оÑĢаÑı
    -0.09
    SystemService
    -0.09
    ugins
    -0.09
    POSITIVE LOGITS
    Âł
    0.11
    âĢ¦
    0.10
    âĢ¦↵
    0.09
     âĢ¦
    0.08
     [âĢ¦]
    0.08
     âĢ¦↵
    0.08
    ...↵
    0.07
     [âĢ¦]↵
    0.07
    ...
    0.07
     «
    0.06
    Activations Density 5.566%

    No Known Activations