© 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. 17-LLAMASCOPE-RES-131K
    11. 3568
    Prev
    Next
    INDEX
    Explanations

    phrases indicating existence or occurrences

    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
    rier
    -0.06
    tn
    -0.06
    stown
    -0.06
     BTS
    -0.06
     Jab
    -0.05
    ents
    -0.05
    ike
    -0.05
     SOP
    -0.05
     alternate
    -0.05
    ooting
    -0.05
    POSITIVE LOGITS
    lue
    0.09
    ẫu
    0.08
    braco
    0.08
    awei
    0.08
    Äįi
    0.07
    帽
    0.07
    ÛĮدÛĮ
    0.07
    à¹Ģฮ
    0.07
    .metamodel
    0.07
    .gg
    0.07
    Activations Density 0.022%

    No Known Activations