© 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. 16185
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial consequences and health impacts

    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
    ude
    -0.07
     ÑĩÑĤобÑĭ
    -0.06
    913
    -0.06
    ritt
    -0.06
    arend
    -0.06
    .mj
    -0.06
    dej
    -0.06
     necessarily
    -0.06
    330
    -0.06
     aby
    -0.06
    POSITIVE LOGITS
     depending
    0.07
    chwitz
    0.07
    especially
    0.07
    ecz
    0.07
    acock
    0.07
    icularly
    0.07
    depending
    0.07
    aber
    0.07
    //{{
    0.07
     além
    0.07
    Activations Density 0.040%

    No Known Activations