© 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. 108271
    Prev
    Next
    INDEX
    Explanations

    terms related to the state of repair or preservation of objects

    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
    rod
    -0.07
    thing
    -0.07
    rium
    -0.07
    AndWait
    -0.07
    dyn
    -0.06
    ãĥ¬ãĤ¤
    -0.06
     cazzo
    -0.06
    whel
    -0.06
    anus
    -0.06
    dimension
    -0.06
    POSITIVE LOGITS
    uality
    0.08
    ierung
    0.08
    .ManyToMany
    0.07
    uzzer
    0.06
    egg
    0.06
    liness
    0.06
    375
    0.06
    /power
    0.06
    iert
    0.06
    pieces
    0.06
    Activations Density 0.007%

    No Known Activations