© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 89249
    Prev
    Next
    INDEX
    Explanations

    expressions related to collective harm and interconnectedness

    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
    ONO
    -0.07
    obl
    -0.07
    osphere
    -0.06
    ContentSize
    -0.06
     compos
    -0.06
    idge
    -0.06
    deo
    -0.06
    ίÏĦ
    -0.06
     mơ
    -0.06
    shint
    -0.06
    POSITIVE LOGITS
    arrants
    0.07
    ascar
    0.07
     done
    0.06
     заÑģÑĤ
    0.06
     Lub
    0.06
    auer
    0.06
     intellig
    0.06
     lubric
    0.06
    agg
    0.06
    zÅij
    0.06
    Activations Density 0.003%

    No Known Activations