© 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. 17-LLAMASCOPE-RES-131K
    6. 74631
    Prev
    Next
    INDEX
    Explanations

    structured data formats, particularly JSON

    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
    bie
    -0.07
    azzo
    -0.06
    isel
    -0.06
    aeda
    -0.06
    ATUS
    -0.06
    ennie
    -0.06
    bul
    -0.06
    bat
    -0.06
    alach
    -0.06
    ead
    -0.06
    POSITIVE LOGITS
    agnostics
    0.07
    μιÏĥ
    0.06
    ãĤ·ãĥ¼
    0.06
     OrderedDict
    0.06
    елеÑĦ
    0.06
    IVERS
    0.06
     Serializable
    0.06
    FolderPath
    0.06
     Hick
    0.06
     toJSON
    0.06
    Activations Density 0.025%

    No Known Activations