© 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. 78157
    Prev
    Next
    INDEX
    Explanations

    references to the word "this"

    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
    -bin
    -0.08
    fox
    -0.08
    llu
    -0.07
     Rencontres
    -0.07
    phia
    -0.07
    ì²´
    -0.06
     boj
    -0.06
    abox
    -0.06
    Synopsis
    -0.06
     bin
    -0.06
    POSITIVE LOGITS
    rol
    0.07
    tribute
    0.07
    apy
    0.07
     roll
    0.07
     rolls
    0.07
     Roll
    0.07
    wie
    0.06
     Rolls
    0.06
     rol
    0.06
    425
    0.06
    Activations Density 0.001%

    No Known Activations