© 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. 105402
    Prev
    Next
    INDEX
    Explanations

    mentions of "local" in various contexts

    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
    aeper
    -0.08
    avers
    -0.08
    itele
    -0.07
    rapy
    -0.07
    ãĤ·ãĤ§
    -0.07
    áme
    -0.07
    uncture
    -0.07
    èª
    -0.07
    ále
    -0.07
    .GetEnumerator
    -0.07
    POSITIVE LOGITS
    ÂIJ
    0.06
    pole
    0.06
     sung
    0.06
    tera
    0.06
    EV
    0.05
     ob
    0.05
    is
    0.05
    angular
    0.05
     net
    0.05
    948
    0.05
    Activations Density 0.000%

    No Known Activations