© 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. 76983
    Prev
    Next
    INDEX
    Explanations

    key verbs and comparative phrases related to treatment and evaluation

    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
    legg
    -0.07
    llib
    -0.07
    ADIO
    -0.07
    uib
    -0.07
    inas
    -0.06
    ÙĬÙħÙĬ
    -0.06
    èĪ
    -0.06
    gg
    -0.06
    izr
    -0.06
    anske
    -0.06
    POSITIVE LOGITS
     rencont
    0.07
    fe
    0.06
    ChangedEventArgs
    0.06
    -li
    0.06
    миниÑģÑĤÑĢа
    0.06
     Lester
    0.06
    enario
    0.06
    -fe
    0.06
     freeze
    0.06
    abay
    0.06
    Activations Density 0.000%

    No Known Activations