© 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. 95040
    Prev
    Next
    INDEX
    Explanations

    specific locations, landmarks, and attractions related to travel experiences

    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
    ilan
    -0.09
    @qq
    -0.09
    xaa
    -0.08
    Sharper
    -0.08
    .IsNullOr
    -0.08
    HomeAsUp
    -0.08
    pras
    -0.08
     mastur
    -0.08
     è©ķ価
    -0.07
    VERR
    -0.07
    POSITIVE LOGITS
     or
    0.09
     versus
    0.07
     oder
    0.06
    uxtap
    0.06
    еÑĤÑĥ
    0.06
     ou
    0.06
     Bishop
    0.06
     ;
    0.05
     Levine
    0.05
     vs
    0.05
    Activations Density 0.052%

    No Known Activations