© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 103976
    Prev
    Next
    INDEX
    Explanations

    numbers and values related to data or statistics

    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
    unami
    -0.07
    essen
    -0.07
    ös
    -0.06
    elves
    -0.06
    udeau
    -0.06
    ements
    -0.06
    loud
    -0.06
    RIA
    -0.05
    egan
    -0.05
    APE
    -0.05
    POSITIVE LOGITS
     lem
    0.07
    -series
    0.07
    ìĽĶë¶ĢíĦ°
    0.07
    _ble
    0.06
     traveller
    0.06
    cheng
    0.06
    oggles
    0.06
    oven
    0.06
    asic
    0.06
    ιβ
    0.06
    Activations Density 0.028%

    No Known Activations