© 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. 39256
    Prev
    Next
    INDEX
    Explanations

    elements related to music and film references

    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
    moduleId
    -0.08
     ãĤĦ
    -0.07
    allet
    -0.07
    ambi
    -0.07
     Painter
    -0.07
    ollen
    -0.07
     undermin
    -0.07
    öy
    -0.06
    важ
    -0.06
    ãĥ¼ãĥĸãĥ«
    -0.06
    POSITIVE LOGITS
     lead
    0.07
     realization
    0.06
    eso
    0.06
     vit
    0.06
     лиÑĨа
    0.05
    ORIA
    0.05
    CanBe
    0.05
     realized
    0.05
     bl
    0.05
     CharSequence
    0.05
    Activations Density 0.007%

    No Known Activations