© 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. 15-LLAMASCOPE-RES-131K
    11. 103199
    Prev
    Next
    INDEX
    Explanations

    personal expressions of opinion or emotion

    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
    ary
    -0.07
    หม
    -0.07
    ories
    -0.06
    اØŃ
    -0.06
    Mixin
    -0.06
    ory
    -0.06
    OC
    -0.06
    271
    -0.06
    519
    -0.06
    ahu
    -0.06
    POSITIVE LOGITS
     personally
    0.08
    iculos
    0.08
    vÄĽd
    0.07
    ripp
    0.07
    orer
    0.07
     vacancy
    0.07
     toi
    0.07
    ?key
    0.06
    quito
    0.06
    aise
    0.06
    Activations Density 0.028%

    No Known Activations