© 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 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. 40542
    Prev
    Next
    INDEX
    Explanations

    negative sentiments towards entertainment or media, particularly movies

    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
    ãĥ³ãĥĸ
    -0.08
    CLUDING
    -0.06
    _GF
    -0.06
    _SW
    -0.06
    yny
    -0.06
     lẫn
    -0.06
    ÑĤÑĢо
    -0.06
    563
    -0.06
    اÙĦÙĩ
    -0.06
    _TS
    -0.06
    POSITIVE LOGITS
     even
    0.31
    even
    0.26
     Even
    0.24
    Even
    0.23
     EVEN
    0.23
     даже
    0.19
     sogar
    0.19
    _even
    0.18
     навÑĸÑĤÑĮ
    0.16
     incluso
    0.16
    Activations Density 0.051%

    No Known Activations