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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5161
    Prev
    Next
    INDEX
    Explanations

    references to cases of military misconduct and criminal accountability

    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
    lop
    -0.07
     adj
    -0.06
     workforce
    -0.06
     cust
    -0.06
    haps
    -0.06
     exp
    -0.06
     analog
    -0.06
    465
    -0.06
    ASE
    -0.06
    tha
    -0.06
    POSITIVE LOGITS
     SEAL
    0.10
     Afghanistan
    0.08
     Afghan
    0.08
    illow
    0.07
    unar
    0.07
    /licenses
    0.07
     Taliban
    0.07
    owan
    0.07
     Seal
    0.07
     Berg
    0.07
    Activations Density 0.030%

    No Known Activations