© 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. 84311
    Prev
    Next
    INDEX
    Explanations

    terms related to consequences, impacts, and values in various contexts

    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
    ortal
    -0.08
    agh
    -0.07
    storybook
    -0.07
    “He
    -0.07
    267
    -0.06
    对æĸ¹
    -0.06
    ighbor
    -0.06
    edia
    -0.06
    porno
    -0.06
    CLAIM
    -0.06
    POSITIVE LOGITS
     him
    0.12
     his
    0.11
     me
    0.11
     us
    0.10
     you
    0.10
     sua
    0.10
    èĩªå·±
    0.10
     their
    0.09
     jego
    0.09
     suas
    0.09
    Activations Density 0.003%

    No Known Activations