© 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. 9-LLAMASCOPE-RES-131K
    11. 95105
    Prev
    Next
    INDEX
    Explanations

    terms related to solicitation and investment offers

    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
    AMI
    -0.07
    oe
    -0.06
    eph
    -0.06
    iets
    -0.06
    oce
    -0.06
     yo
    -0.06
    itted
    -0.06
    zell
    -0.06
    iveau
    -0.06
    ixon
    -0.06
    POSITIVE LOGITS
    iquid
    0.07
    дон
    0.06
     slick
    0.06
    .ci
    0.06
    addtogroup
    0.06
    urons
    0.06
    dens
    0.06
    uran
    0.06
     McKay
    0.06
    FORCE
    0.06
    Activations Density 0.001%

    No Known Activations