© 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. 17-LLAMASCOPE-RES-131K
    11. 125256
    Prev
    Next
    INDEX
    Explanations

    content related to educational courses and participant engagement

    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
    akk
    -0.06
    arine
    -0.06
     contest
    -0.06
     final
    -0.06
     contests
    -0.06
    indle
    -0.06
    haled
    -0.06
    nia
    -0.05
    kish
    -0.05
     Contest
    -0.05
    POSITIVE LOGITS
    tach
    0.08
    singleton
    0.07
    ingroup
    0.07
    NCY
    0.07
    __$
    0.07
    ãĥ³ãĥij
    0.07
     tantra
    0.07
    ungan
    0.07
    reesome
    0.07
    аÑģÑģив
    0.07
    Activations Density 0.002%

    No Known Activations