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. 84251
    Prev
    Next
    INDEX
    Explanations

    terms related to offensive strategies and actions

    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
    +offset
    -0.09
    oral
    -0.08
    nez
    -0.08
    нез
    -0.07
    oris
    -0.07
    dera
    -0.07
    ily
    -0.07
    oria
    -0.06
    ilk
    -0.06
    uckets
    -0.06
    POSITIVE LOGITS
    ensively
    0.08
    anagan
    0.08
    /off
    0.07
    ifer
    0.07
    entlich
    0.07
    ive
    0.07
    /on
    0.07
    ally
    0.07
    /support
    0.06
    portun
    0.06
    Activations Density 0.009%

    No Known Activations