© 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. 27563
    Prev
    Next
    INDEX
    Explanations

    references to time and significant events or milestones

    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
    OutOfBounds
    -0.08
    мп
    -0.07
    eki
    -0.07
    "struct
    -0.07
    upal
    -0.07
    íĮ
    -0.07
    erais
    -0.07
     insp
    -0.07
    upa
    -0.07
     dieta
    -0.07
    POSITIVE LOGITS
     always
    0.06
     sized
    0.06
     Fam
    0.06
     familiar
    0.05
     never
    0.05
     exactly
    0.05
     maybe
    0.05
    .
    0.05
    509
    0.05
    icorn
    0.05
    Activations Density 0.000%

    No Known Activations