© 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 EvalsExportsinterp-engineNEWAPI 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. 2254
    Prev
    Next
    INDEX
    Explanations

    phrases related to public opinion and acceptance

    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
    elho
    -0.07
    akk
    -0.07
     æķħ
    -0.07
     èIJ
    -0.07
    ighet
    -0.07
    673
    -0.07
    ovu
    -0.07
     Kear
    -0.07
    imon
    -0.07
     cụ
    -0.06
    POSITIVE LOGITS
     already
    0.07
    åıªè¦ģ
    0.07
     simply
    0.07
     merely
    0.07
     worse
    0.06
     knowing
    0.06
    æ¯ķ
    0.06
     Already
    0.06
    adir
    0.06
     anyway
    0.06
    Activations Density 0.043%

    No Known Activations