© 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. 117871
    Prev
    Next
    INDEX
    Explanations

    words and variations related to installation processes or actions

    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
    itin
    -0.07
    icz
    -0.07
    unya
    -0.07
    imuth
    -0.07
    edom
    -0.07
    ertz
    -0.07
    andas
    -0.06
    èĻ«
    -0.06
    PCM
    -0.06
    asan
    -0.06
    POSITIVE LOGITS
    s
    0.07
    ONGL
    0.07
    oppable
    0.07
    ad
    0.06
    dl
    0.06
    ensa
    0.06
    allback
    0.06
    ling
    0.06
    ALLED
    0.06
    OSH
    0.06
    Activations Density 0.012%

    No Known Activations