© 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. 105403
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaborative actions or communal activities

    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
    orton
    -0.08
    #
    -0.07
    oogle
    -0.07
    梨
    -0.07
    prox
    -0.07
    amina
    -0.07
     Sexe
    -0.07
    mel
    -0.07
    uve
    -0.07
    arent
    -0.06
    POSITIVE LOGITS
    çĿ
    0.07
    kı
    0.06
    ãĥªãĤ¢
    0.06
     Ib
    0.06
    ç¿Ĵ
    0.06
    arsity
    0.06
     quasi
    0.05
    -fw
    0.05
     sque
    0.05
    combo
    0.05
    Activations Density 0.002%

    No Known Activations