© 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. 94715
    Prev
    Next
    INDEX
    Explanations

    occurrences of copyright and licensing statements

    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
    ison
    -0.07
    498
    -0.06
     Bet
    -0.06
    ML
    -0.06
    2
    -0.06
    -on
    -0.05
    erver
    -0.05
    stat
    -0.05
    898
    -0.05
    it
    -0.05
    POSITIVE LOGITS
    VERR
    0.08
     poil
    0.08
    oppel
    0.08
    ModelProperty
    0.08
    emoc
    0.08
    ekil
    0.08
    olah
    0.08
    erli
    0.08
    Äįet
    0.08
    sWith
    0.07
    Activations Density 0.001%

    No Known Activations