© 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. 125981
    Prev
    Next
    INDEX
    Explanations

    phrases that signal conclusions or summarizations

    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
    )((((
    -0.07
    ocaly
    -0.07
    ovu
    -0.07
    OCR
    -0.07
    Shift
    -0.07
    ldr
    -0.07
    ubar
    -0.06
    rak
    -0.06
    ewire
    -0.06
    exels
    -0.06
    POSITIVE LOGITS
    ivet
    0.07
    -called
    0.07
    ber
    0.06
     naturally
    0.06
    alist
    0.06
     why
    0.06
    recision
    0.06
    sled
    0.06
    hardt
    0.06
    aring
    0.06
    Activations Density 0.020%

    No Known Activations