© 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. 117708
    Prev
    Next
    INDEX
    Explanations

    instances of the pronouns "we" and "us"

    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
    asma
    -0.06
     пÑĢиÑĤ
    -0.06
     Consult
    -0.06
    legen
    -0.06
     Terminal
    -0.06
    f
    -0.06
     coloured
    -0.06
     consultancy
    -0.06
    isl
    -0.06
    se
    -0.05
    POSITIVE LOGITS
     host
    0.07
    NCY
    0.07
    Host
    0.07
    vlc
    0.07
     hosts
    0.07
    vanished
    0.07
    emann
    0.07
    erset
    0.07
    ByVersion
    0.07
    ¼
    0.06
    Activations Density 0.022%

    No Known Activations