© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 89812
    Prev
    Next
    INDEX
    Explanations

    numerical values related to product specifications or model numbers

    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
     den
    -0.07
    angl
    -0.06
    anax
    -0.06
    alc
    -0.06
    tml
    -0.06
    ilent
    -0.06
    odzi
    -0.06
    lider
    -0.06
    ktop
    -0.06
    ects
    -0.06
    POSITIVE LOGITS
    ãĥ³ãĤ¬
    0.08
    Ìģc
    0.08
    fea
    0.07
     skl
    0.07
    .MixedReality
    0.07
    овий
    0.07
    #ad
    0.07
    #echo
    0.06
    iteur
    0.06
    ãģĤãģ£ãģŁ
    0.06
    Activations Density 0.039%

    No Known Activations