© 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. 9-LLAMASCOPE-RES-131K
    11. 98089
    Prev
    Next
    INDEX
    Explanations

    references to instructional DVDs and training materials

    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
     adj
    -0.07
     minim
    -0.06
     maxim
    -0.06
    -0.06
     unf
    -0.06
     past
    -0.05
     du
    -0.05
     Ho
    -0.05
     Du
    -0.05
     biological
    -0.05
    POSITIVE LOGITS
    acket
    0.09
    оÑĢалÑĮ
    0.08
    ocre
    0.08
    Ïģιο
    0.08
    .nano
    0.08
    ibox
    0.08
    оÑĢоÑĪ
    0.08
    _eth
    0.08
    nish
    0.07
     å®®
    0.07
    Activations Density 0.028%

    No Known Activations