© 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. 89369
    Prev
    Next
    INDEX
    Explanations

    references to specific routes or paths

    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
    halb
    -0.07
    wit
    -0.07
    ITES
    -0.07
    pom
    -0.07
    ÏĥÏĦαÏĥη
    -0.06
    IOC
    -0.06
    952
    -0.06
    ëĬ¥
    -0.06
    rico
    -0.06
    ultz
    -0.06
    POSITIVE LOGITS
    inely
    0.09
    omb
    0.07
    ache
    0.06
    (Route
    0.06
    orama
    0.06
    تÙĥ
    0.06
    du
    0.06
    ông
    0.06
    66
    0.06
    ledge
    0.06
    Activations Density 0.007%

    No Known Activations