© 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. 29334
    Prev
    Next
    INDEX
    Explanations

    expressions of familial love and communication

    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
    uet
    -0.07
    athy
    -0.07
    du
    -0.07
    ucc
    -0.07
    atham
    -0.06
    669
    -0.06
    iny
    -0.06
    00
    -0.06
     tattoos
    -0.06
    wards
    -0.06
    POSITIVE LOGITS
     signature
    0.18
     signatures
    0.16
    signature
    0.16
    Signature
    0.16
     Signature
    0.15
     Signed
    0.15
     signed
    0.15
     signing
    0.14
    signed
    0.14
    Signed
    0.14
    Activations Density 0.069%

    No Known Activations