© 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. 17-LLAMASCOPE-RES-131K
    11. 118607
    Prev
    Next
    INDEX
    Explanations

    descriptions of emotional depth and complexity in narratives

    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
    enchmark
    -0.06
    oler
    -0.06
    ish
    -0.06
    230
    -0.06
     reasons
    -0.06
    isen
    -0.06
    erg
    -0.06
    ied
    -0.05
    145
    -0.05
    865
    -0.05
    POSITIVE LOGITS
    .alloc
    0.08
     equivalent
    0.07
    precision
    0.07
    ATAR
    0.07
    epam
    0.07
    룹
    0.07
    ichel
    0.07
    .Sdk
    0.07
    dorf
    0.07
     precision
    0.07
    Activations Density 0.027%

    No Known Activations