© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 104062
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs in various tenses

    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
    ipt
    -0.08
    .datab
    -0.07
     Wilkinson
    -0.07
    uyết
    -0.07
    ibi
    -0.06
     Rosenberg
    -0.06
    erville
    -0.06
    enn
    -0.06
    .neo
    -0.06
    plx
    -0.06
    POSITIVE LOGITS
    canf
    0.07
    gba
    0.06
    .failure
    0.06
    jang
    0.06
    ylon
    0.06
    ynos
    0.06
    endi
    0.06
    aviest
    0.06
    OLEAN
    0.06
     Erf
    0.06
    Activations Density 0.035%

    No Known Activations