© 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. 4288
    Prev
    Next
    INDEX
    Explanations

    references to months and significant dates

    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
    alet
    -0.07
    awan
    -0.06
    incinn
    -0.06
    Kit
    -0.06
    olk
    -0.06
    eny
    -0.06
     Haven
    -0.06
    arity
    -0.06
    िà¤
    -0.06
     mort
    -0.06
    POSITIVE LOGITS
    201
    0.08
    202
    0.07
    ó
    0.07
    ÑįÑĤомÑĥ
    0.07
     jl
    0.07
    197
    0.07
    bruar
    0.07
    ANGLE
    0.06
    utter
    0.06
    atham
    0.06
    Activations Density 0.007%

    No Known Activations