© 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. 104425
    Prev
    Next
    INDEX
    Explanations

    sections related to climate actions and sustainability initiatives

    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
    TECTED
    -0.06
    zy
    -0.06
    USED
    -0.06
    _startup
    -0.06
    elix
    -0.06
     Haupt
    -0.06
    Stick
    -0.06
    nop
    -0.05
    stick
    -0.05
    æ¹
    -0.05
    POSITIVE LOGITS
     penc
    0.08
     KW
    0.07
    icina
    0.07
    .Dev
    0.06
     green
    0.06
     embr
    0.06
    commit
    0.06
    green
    0.06
    ngx
    0.06
    .dev
    0.06
    Activations Density 0.039%

    No Known Activations