© 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. 9-LLAMASCOPE-RES-131K
    11. 98155
    Prev
    Next
    INDEX
    Explanations

    references to companionship and family dynamics

    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
    bour
    -0.07
    templ
    -0.07
    ÄIJT
    -0.07
    decess
    -0.07
    emouth
    -0.06
    ');?>"
    -0.06
    TA
    -0.06
    ĺ认
    -0.06
    branch
    -0.06
    branches
    -0.06
    POSITIVE LOGITS
    288
    0.07
    iba
    0.07
    274
    0.07
    847
    0.06
    zon
    0.06
    534
    0.06
    chter
    0.06
    rvé
    0.06
    287
    0.06
     Sed
    0.06
    Activations Density 0.002%

    No Known Activations