© 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. 59020
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal conviction or strong opinion on social issues

    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
     useClass
    -0.06
     sobie
    -0.05
    oves
    -0.05
    AGAIN
    -0.05
    imen
    -0.05
    vetica
    -0.05
    aspberry
    -0.05
    enance
    -0.05
    両
    -0.05
     både
    -0.05
    POSITIVE LOGITS
     other
    0.51
    other
    0.40
    åħ¶ä»ĸ
    0.38
     autres
    0.36
     Other
    0.36
     OTHER
    0.35
    Other
    0.34
     others
    0.34
    -other
    0.34
     otros
    0.33
    Activations Density 0.108%

    No Known Activations