© 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. 62612
    Prev
    Next
    INDEX
    Explanations

    references to cultural criticism in media

    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
    енÑģ
    -0.07
    기ê°Ģ
    -0.06
    raud
    -0.06
    asmus
    -0.06
    eniz
    -0.06
    cket
    -0.06
    гов
    -0.06
     ëķĮ문
    -0.06
     tempfile
    -0.06
    owied
    -0.06
    POSITIVE LOGITS
     how
    0.10
    how
    0.08
     including
    0.08
     its
    0.08
    including
    0.07
    åıĬåħ¶
    0.07
    INCLUDING
    0.07
    -how
    0.07
    indr
    0.07
    Including
    0.07
    Activations Density 0.030%

    No Known Activations