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. 17-LLAMASCOPE-RES-131K
    6. 125568
    Prev
    Next
    INDEX
    Explanations

    references to violence and combat situations

    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
    GuidId
    -0.09
    icros
    -0.08
    sgi
    -0.08
    abyrin
    -0.08
    entialAction
    -0.08
    AREST
    -0.08
    chwitz
    -0.08
    ennie
    -0.08
    uzey
    -0.08
    oại
    -0.08
    POSITIVE LOGITS
     Composition
    0.06
     compositions
    0.06
     advancing
    0.06
    ox
    0.06
     loyal
    0.06
     å£
    0.05
     rank
    0.05
     unfortunate
    0.05
    erville
    0.05
    leader
    0.05
    Activations Density 0.024%

    No Known Activations