© 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. 40577
    Prev
    Next
    INDEX
    Explanations

    instances of significant figures or entities in text

    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
    hs
    -0.06
    stantial
    -0.06
     Powers
    -0.06
    odÃŃ
    -0.06
    434
    -0.06
    ina
    -0.05
    ollo
    -0.05
    rell
    -0.05
    æĥ³åĪ°
    -0.05
    rf
    -0.05
    POSITIVE LOGITS
    awy
    0.07
    lamaz
    0.07
    zar
    0.07
    "label
    0.07
    smarty
    0.07
     also
    0.07
    inker
    0.06
    zk
    0.06
    andr
    0.06
    EDIA
    0.06
    Activations Density 0.015%

    No Known Activations