© 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. 54195
    Prev
    Next
    INDEX
    Explanations

    instances of citations and references in the text

    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
    loff
    -0.07
    otr
    -0.06
    zac
    -0.06
    urt
    -0.06
     res
    -0.06
     Dough
    -0.06
    eck
    -0.06
    ÐľÐŀ
    -0.06
    ont
    -0.05
    eller
    -0.05
    POSITIVE LOGITS
    0.08
    ynet
    0.07
    lendi
    0.07
    oves
    0.07
    onymous
    0.07
     conduc
    0.07
    FORCE
    0.07
    .ci
    0.07
    adow
    0.07
     jour
    0.07
    Activations Density 0.030%

    No Known Activations