© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 107216
    Prev
    Next
    INDEX
    Explanations

    phrases that express frustration or disappointment in relationships and situations

    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
    ière
    -0.08
    alia
    -0.07
    akat
    -0.07
    akah
    -0.07
    ikki
    -0.07
    .getvalue
    -0.07
    usk
    -0.07
    akra
    -0.07
    UserCode
    -0.07
    unken
    -0.07
    POSITIVE LOGITS
     promises
    0.13
     promise
    0.13
     promised
    0.11
     Promise
    0.10
     promising
    0.10
    promise
    0.09
    Promise
    0.09
     assurances
    0.09
     surely
    0.08
     assurance
    0.07
    Activations Density 0.070%

    No Known Activations