© 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. 27251
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases that indicate continuation or addition of ideas

    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
    ych
    -0.07
    нен
    -0.07
    portlet
    -0.07
    sharp
    -0.07
     Enough
    -0.06
    _scaling
    -0.06
     enough
    -0.06
    rve
    -0.06
    anners
    -0.06
    avings
    -0.06
    POSITIVE LOGITS
     than
    0.23
    than
    0.21
    -than
    0.19
    _than
    0.18
     THAN
    0.16
    Than
    0.16
     Than
    0.15
     niż
    0.14
     než
    0.12
    _THAN
    0.11
    Activations Density 0.048%

    No Known Activations