© 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. 15-LLAMASCOPE-RES-131K
    11. 87572
    Prev
    Next
    INDEX
    Explanations

    phrases related to connectivity and interaction with technology

    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
    AME
    -0.06
    illion
    -0.06
    chap
    -0.06
    reopen
    -0.06
    ãĥ¼ãĥĬ
    -0.06
     immune
    -0.06
     flush
    -0.06
    ikk
    -0.06
    imonial
    -0.06
    chod
    -0.06
    POSITIVE LOGITS
    axed
    0.08
     plug
    0.08
     Plug
    0.08
    _into
    0.08
    &action
    0.07
    edback
    0.07
    /un
    0.07
    atters
    0.07
    Plug
    0.07
    anned
    0.07
    Activations Density 0.005%

    No Known Activations