© 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. 55875
    Prev
    Next
    INDEX
    Explanations

    words associated with warfare or military conflicts

    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
    rego
    -0.08
    ç¯ĩ
    -0.08
    ãĥĥãĥĦ
    -0.07
    ãĢĤ↵↵↵↵↵↵
    -0.07
    gın
    -0.07
    Enlarge
    -0.07
    .fake
    -0.07
    ayıp
    -0.07
    iverz
    -0.07
    .Extension
    -0.07
    POSITIVE LOGITS
    venida
    0.06
    £
    0.06
    tir
    0.06
    uncture
    0.06
    ochen
    0.06
    ufe
    0.05
     lesbi
    0.05
    vel
    0.05
    jez
    0.05
    ess
    0.05
    Activations Density 0.000%

    No Known Activations