© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71605
    Prev
    Next
    INDEX
    Explanations

    themes related to government secrecy and 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
    SEG
    -0.07
    ä¸Ī
    -0.07
     Camping
    -0.06
    ÙĦاÙħ
    -0.06
    mediate
    -0.06
    atak
    -0.06
    bands
    -0.06
    90
    -0.06
    /sign
    -0.06
     bail
    -0.06
    POSITIVE LOGITS
     Branch
    0.07
    Branch
    0.07
     CIA
    0.07
    Courier
    0.07
     hyp
    0.07
     overseas
    0.06
     Predator
    0.06
    rana
    0.06
     Overse
    0.06
    hyp
    0.06
    Activations Density 0.004%

    No Known Activations