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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87855
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and positive experiences related to events or services

    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
    анÑĤ
    -0.07
    antal
    -0.06
    ucky
    -0.06
    ipe
    -0.06
    cesso
    -0.06
    ahr
    -0.06
    اسÛĮ
    -0.06
    arem
    -0.06
    inan
    -0.06
    uling
    -0.06
    POSITIVE LOGITS
    VERR
    0.08
    Overall
    0.08
     Overall
    0.08
    ÙĪØ±ÛĮ
    0.08
    overall
    0.07
    .truth
    0.07
     disap
    0.07
    unu
    0.07
     absolutely
    0.07
    ÅĻez
    0.07
    Activations Density 0.020%

    No Known Activations