Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4866
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "gh," which seem to signify emotional states or reactions

    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
    تاÙĨ
    -0.07
    ipa
    -0.07
    õi
    -0.06
    .dex
    -0.06
    iyan
    -0.06
    iped
    -0.06
    еÑģÑĮ
    -0.06
    hea
    -0.06
    abeth
    -0.06
    ÑħÑĥ
    -0.06
    POSITIVE LOGITS
    tright
    0.10
    gh
    0.09
     Gh
    0.08
     gh
    0.08
    etto
    0.07
    opper
    0.07
    urst
    0.07
    _inches
    0.07
    onor
    0.07
    esda
    0.07
    Activations Density 0.012%

    No Known Activations