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

    Neuronpedia

    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. 22-LLAMASCOPE-RES-131K
    11. 3616
    Prev
    Next
    INDEX
    Explanations

    statements about language usage and political labeling

    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
    argin
    -0.07
    stroy
    -0.07
    물ìĿĦ
    -0.07
    alten
    -0.07
    è¾ij
    -0.06
    longleftrightarrow
    -0.06
    arty
    -0.06
    .lin
    -0.06
    avou
    -0.06
    omed
    -0.06
    POSITIVE LOGITS
     talk
    0.18
     talking
    0.15
     talks
    0.14
     say
    0.14
     talked
    0.14
    talk
    0.14
     refer
    0.13
     Talk
    0.13
    -talk
    0.13
     referring
    0.13
    Activations Density 0.044%

    No Known Activations