© 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. 15-LLAMASCOPE-RES-131K
    6. 1044
    Prev
    Next
    INDEX
    Explanations

    elements related to geographic or cultural references

    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
     Fors
    -0.07
    oki
    -0.06
     plastic
    -0.06
    hazi
    -0.06
     earlier
    -0.05
    ondo
    -0.05
    iju
    -0.05
    irsch
    -0.05
     Zag
    -0.05
     Pom
    -0.05
    POSITIVE LOGITS
    æĬ¼
    0.07
    arius
    0.07
     Wenger
    0.07
    جر
    0.07
     Ấ
    0.07
    ruk
    0.07
    eyim
    0.07
    á»§
    0.07
    unte
    0.07
    ãĥ¼ãĥį
    0.07
    Activations Density 0.010%

    No Known Activations