© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125829
    Prev
    Next
    INDEX
    Explanations

    CSS properties and values related to styling elements

    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
    .shtml
    -0.08
    -fontawesome
    -0.08
    ECH
    -0.07
    öz
    -0.07
    omon
    -0.07
     Annunci
    -0.07
    ษ
    -0.06
    ahun
    -0.06
    rowned
    -0.06
    azio
    -0.06
    POSITIVE LOGITS
     light
    0.06
    ived
    0.06
    imei
    0.06
    kov
    0.06
    ulos
    0.06
    ungs
    0.06
     supp
    0.05
     Whe
    0.05
     Follow
    0.05
    िà¤Ń
    0.05
    Activations Density 0.001%

    No Known Activations