© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 96819
    Prev
    Next
    INDEX
    Explanations

    email addresses and URL formats

    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
     addCriterion
    -0.08
    .scalablytyped
    -0.08
    CCCCCC
    -0.07
    coon
    -0.07
    ɵ
    -0.07
    lém
    -0.07
    cano
    -0.07
    stagram
    -0.07
    ceptar
    -0.07
    óst
    -0.06
    POSITIVE LOGITS
     mem
    0.06
     kali
    0.06
    eler
    0.06
    icer
    0.05
     Christian
    0.05
     gl
    0.05
    ULO
    0.05
    106
    0.05
     Arbor
    0.05
    elow
    0.05
    Activations Density 0.029%

    No Known Activations