© 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. 9-LLAMASCOPE-RES-131K
    6. 95628
    Prev
    Next
    INDEX
    Explanations

    instances of LaTeX commands and structures

    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
    ulen
    -0.07
    ULE
    -0.07
    ature
    -0.07
    arkin
    -0.07
    edback
    -0.07
    asto
    -0.07
    MLS
    -0.07
    inge
    -0.07
    SizeMode
    -0.07
    ish
    -0.06
    POSITIVE LOGITS
     Bene
    0.06
    å©·
    0.06
    (equalTo
    0.06
    åĿª
    0.06
     Ferry
    0.06
    lıģ
    0.06
     Dort
    0.06
    arth
    0.06
    ãĥ³ãĤ°
    0.06
    gra
    0.05
    Activations Density 0.007%

    No Known Activations