© 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. 106753
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the act of placing something in a significant or impactful role

    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
     Vul
    -0.07
    iek
    -0.06
    ubar
    -0.06
     adultes
    -0.06
    asons
    -0.06
    orton
    -0.06
    ube
    -0.06
     Lev
    -0.06
     Karma
    -0.06
     bub
    -0.06
    POSITIVE LOGITS
     emphasis
    0.08
    ETO
    0.07
    .ManyToMany
    0.07
    emphasis
    0.07
    BCM
    0.07
    λοÏĤ
    0.07
     strain
    0.07
    dden
    0.07
    éļİ
    0.07
    phasis
    0.06
    Activations Density 0.012%

    No Known Activations