© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 70967
    Prev
    Next
    INDEX
    Explanations

    references to violent events and the reactions surrounding them

    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
    arp
    -0.08
    .TabStop
    -0.08
    lems
    -0.07
    ÅĻes
    -0.07
    vak
    -0.07
    eatures
    -0.07
    ampa
    -0.07
    ãĥ¯ãĥ¼
    -0.07
    jerne
    -0.07
    ghan
    -0.07
    POSITIVE LOGITS
    oni
    0.07
     Israelis
    0.06
    pora
    0.06
     Daly
    0.05
    ickey
    0.05
     Israeli
    0.05
     Operator
    0.05
    Dash
    0.05
    ×
    0.05
     IDF
    0.05
    Activations Density 0.009%

    No Known Activations