© 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. 9-LLAMASCOPE-RES-131K
    11. 96754
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to interpersonal relationships and connections

    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
    .grpc
    -0.07
    wyn
    -0.07
    ãĤ¹ãĥŀ
    -0.07
    ein
    -0.07
     Wich
    -0.07
    isci
    -0.07
    wan
    -0.07
    vette
    -0.06
    lein
    -0.06
    ringe
    -0.06
    POSITIVE LOGITS
    /her
    0.11
    /us
    0.10
    /th
    0.10
    self
    0.09
    iner
    0.08
    atically
    0.08
    chy
    0.08
    ched
    0.07
     же
    0.07
    /il
    0.07
    Activations Density 0.106%

    No Known Activations