© 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 EvalsExportsAPI 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. 60889
    Prev
    Next
    INDEX
    Explanations

    phrases related to support and assistance in various contexts

    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
     Irr
    -0.06
     retal
    -0.06
     UFO
    -0.06
     wide
    -0.06
     Rosenstein
    -0.06
     mechan
    -0.06
    kal
    -0.06
    OutputStream
    -0.06
    wide
    -0.06
    OnInit
    -0.06
    POSITIVE LOGITS
    agli
    0.09
    Safety
    0.08
     safely
    0.08
     Safety
    0.08
    Danger
    0.08
    ToRemove
    0.07
     SAF
    0.07
    EGIN
    0.07
     safety
    0.07
    adh
    0.07
    Activations Density 0.001%

    No Known Activations