© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 106244
    Prev
    Next
    INDEX
    Explanations

    themes related to ideological and religious 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
    CLR
    -0.08
    Shot
    -0.07
    phinx
    -0.07
    hiba
    -0.07
    iable
    -0.07
    itra
    -0.07
    inde
    -0.07
    293
    -0.07
     Seal
    -0.07
    forum
    -0.07
    POSITIVE LOGITS
     others
    0.08
     Others
    0.07
     intolerance
    0.07
     superiority
    0.07
    ropa
    0.06
     exclus
    0.06
     pros
    0.06
     dog
    0.06
     intoler
    0.06
     insistence
    0.06
    Activations Density 0.052%

    No Known Activations