© 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. 836
    Prev
    Next
    INDEX
    Explanations

    numerical data related to household and family income

    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
    ijke
    -0.07
    iaz
    -0.07
    vice
    -0.07
    :CGRect
    -0.07
    aci
    -0.07
    upy
    -0.07
    adin
    -0.07
    ysz
    -0.07
    uely
    -0.07
    kiem
    -0.06
    POSITIVE LOGITS
    ertia
    0.06
    ìĦ¼
    0.06
     infl
    0.06
    ارت
    0.06
    pn
    0.05
     Hav
    0.05
    oden
    0.05
    &oacute
    0.05
    Field
    0.05
    AppComponent
    0.05
    Activations Density 0.001%

    No Known Activations