© 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. 4681
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate origin or source of content

    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
    ibold
    -0.08
    atron
    -0.08
    aye
    -0.07
    ilor
    -0.07
    ASN
    -0.07
    leÅŁik
    -0.07
     án
    -0.07
    ÙĦÙĤ
    -0.07
    .Lib
    -0.07
    haps
    -0.07
    POSITIVE LOGITS
     across
    0.11
     throughout
    0.09
     various
    0.08
     around
    0.08
     anywhere
    0.07
     everywhere
    0.06
     both
    0.06
     past
    0.06
     leading
    0.06
    /ip
    0.06
    Activations Density 0.022%

    No Known Activations