© 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. 41637
    Prev
    Next
    INDEX
    Explanations

    terms related to measurements and evaluation processes

    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
     erg
    -0.06
    eroon
    -0.06
    âĨ
    -0.06
    anova
    -0.06
    my
    -0.06
     choke
    -0.05
    PubMed
    -0.05
    èĤ¡
    -0.05
    umni
    -0.05
    ahn
    -0.05
    POSITIVE LOGITS
     ASTM
    0.08
    TestMethod
    0.08
     è©
    0.08
     test
    0.07
     bench
    0.07
    ulos
    0.07
    試
    0.07
     determination
    0.07
    MethodName
    0.07
    legg
    0.07
    Activations Density 0.007%

    No Known Activations