© 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. 118795
    Prev
    Next
    INDEX
    Explanations

    references to community outreach and engagement activities

    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
    ìĶ©
    -0.08
    ovel
    -0.08
    ially
    -0.08
    cheng
    -0.08
    atures
    -0.08
    rita
    -0.07
    zyst
    -0.07
    isson
    -0.07
    ovo
    -0.07
    otine
    -0.07
    POSITIVE LOGITS
    ByVersion
    0.08
    ive
    0.08
    ting
    0.07
    =out
    0.07
    reach
    0.07
    able
    0.07
    ion
    0.07
    739
    0.07
    ential
    0.06
    ables
    0.06
    Activations Density 0.003%

    No Known Activations