© 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. 78312
    Prev
    Next
    INDEX
    Explanations

    terms related to geography, ethnicity, and various scientific disciplines

    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
    rob
    -0.06
    iran
    -0.06
     Rig
    -0.05
    reat
    -0.05
    536
    -0.05
    922
    -0.05
     proper
    -0.05
     д
    -0.05
    ouro
    -0.05
    mates
    -0.05
    POSITIVE LOGITS
    .grp
    0.08
    ï¼Īç¬ij
    0.08
     hava
    0.07
    drv
    0.07
     (*((
    0.07
    Ñħо
    0.07
    Äįel
    0.07
    ï¼£
    0.07
    ॰
    0.07
    #echo
    0.07
    Activations Density 0.081%

    No Known Activations