© 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. 4733
    Prev
    Next
    INDEX
    Explanations

    references to think tanks and policy research organizations

    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
    ìħ
    -0.07
    éĿ©åij½
    -0.06
     sublic
    -0.06
     oÄį
    -0.06
    ----------------------------------------------------------------------↵
    -0.06
    ëļ
    -0.06
     Pazar
    -0.06
    erken
    -0.05
     buoy
    -0.05
     towns
    -0.05
    POSITIVE LOGITS
     research
    0.08
    research
    0.08
     ìĹ°êµ¬
    0.07
     think
    0.07
     Think
    0.07
    ripp
    0.07
    Think
    0.07
    ignum
    0.07
    think
    0.07
    anol
    0.07
    Activations Density 0.024%

    No Known Activations