Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126276
    Prev
    Next
    INDEX
    Explanations

    emotions related to pain and offense

    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
    akte
    -0.07
    alle
    -0.07
    åĬ
    -0.06
    weise
    -0.06
    FieldType
    -0.06
    fty
    -0.06
    ftime
    -0.06
    inx
    -0.06
    Leader
    -0.06
    ª
    -0.06
    POSITIVE LOGITS
     Nachricht
    0.07
    .scalablytyped
    0.07
    oused
    0.07
    infeld
    0.07
    apps
    0.06
    usp
    0.06
     Marriott
    0.06
     Yard
    0.06
    abant
    0.06
     ì¶ľìŀ¥
    0.06
    Activations Density 0.050%

    No Known Activations