© 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. 30227
    Prev
    Next
    INDEX
    Explanations

    instructions for searching and interacting with online resources

    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
     Kop
    -0.07
    Æ°ng
    -0.06
    Äįas
    -0.06
    çĢ¬
    -0.06
    .GPIO
    -0.06
    енÑĸ
    -0.06
    ãĥ³ãĤ¹
    -0.06
    обÑĢаÐ
    -0.06
    _trampoline
    -0.06
    roz
    -0.06
    POSITIVE LOGITS
     input
    0.11
    -input
    0.10
    input
    0.09
     inputs
    0.09
    Input
    0.09
     Input
    0.09
    _input
    0.09
     Inputs
    0.09
    ukan
    0.08
     query
    0.08
    Activations Density 0.017%

    No Known Activations