© 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. 3817
    Prev
    Next
    INDEX
    Explanations

    numerical values and their relationships in data or statistics

    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
    ëŁ
    -0.07
    anio
    -0.07
    avery
    -0.07
     Truy
    -0.06
    inder
    -0.06
     dagger
    -0.06
    quo
    -0.06
    asket
    -0.06
     isc
    -0.06
    PKG
    -0.06
    POSITIVE LOGITS
     escal
    0.07
    éĽª
    0.06
    olle
    0.06
    ÑĥÑĤÑĮ
    0.06
    erial
    0.06
    ĶåĽŀ
    0.06
    ué
    0.06
    ãĥ¼ãĥ«
    0.06
     Terminal
    0.06
     پشت
    0.06
    Activations Density 0.000%

    No Known Activations