© 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. 87805
    Prev
    Next
    INDEX
    Explanations

    phrases related to expectations and comparisons

    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
    utex
    -0.06
    anz
    -0.06
    oya
    -0.06
    lio
    -0.06
     sleeper
    -0.06
     lantern
    -0.06
    ģµ
    -0.05
    auce
    -0.05
    330
    -0.05
    uzzi
    -0.05
    POSITIVE LOGITS
     typical
    0.14
    typ
    0.12
     typically
    0.11
     Typical
    0.10
    Typ
    0.09
     Typically
    0.09
    typically
    0.09
     commonly
    0.08
    expect
    0.08
     encountered
    0.08
    Activations Density 0.077%

    No Known Activations