© 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. 3186
    Prev
    Next
    INDEX
    Explanations

    punctuations and line breaks in text

    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
    ↵
    -0.06
     close
    -0.06
     c
    -0.06
    oc
    -0.06
     commercial
    -0.06
     (
    -0.06
    202
    -0.06
     former
    -0.05
    -
    -0.05
     classes
    -0.05
    POSITIVE LOGITS
    ebek
    0.10
     âĢı
    0.09
    erece
    0.09
     SaÄŁ
    0.09
    ÑĢиÑĩ
    0.09
    #ad
    0.08
    STYPE
    0.08
    buz
    0.08
    MESS
    0.08
    ebo
    0.08
    Activations Density 0.011%

    No Known Activations