© 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. 17-LLAMASCOPE-RES-131K
    11. 118524
    Prev
    Next
    INDEX
    Explanations

    references to file paths and metadata in code or documentation

    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
    리ì¦Ī
    -0.07
    ugas
    -0.06
     Aero
    -0.06
    ÅĽmy
    -0.06
    ï½ŀï½ŀ
    -0.06
    ÑĸйÑģ
    -0.06
    #error
    -0.06
    èĬ¯
    -0.06
    AndView
    -0.06
    Ping
    -0.06
    POSITIVE LOGITS
    ined
    0.06
    oldt
    0.06
    PACE
    0.06
     taste
    0.06
    id
    0.05
    |wx
    0.05
    itol
    0.05
    uo
    0.05
    oss
    0.05
    irse
    0.05
    Activations Density 0.001%

    No Known Activations