© 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. 29595
    Prev
    Next
    INDEX
    Explanations

    timestamps and formatted date/time information

    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
    sworth
    -0.07
    bracht
    -0.06
     mileage
    -0.06
    çıł
    -0.06
    (ed
    -0.06
     ph
    -0.06
    IDI
    -0.06
    .variable
    -0.06
    ahun
    -0.06
    жд
    -0.06
    POSITIVE LOGITS
    ivent
    0.07
     Tent
    0.06
     split
    0.06
    hon
    0.06
    quia
    0.06
    lando
    0.06
    coal
    0.06
     paci
    0.06
    ãĥ¼ãĥģ
    0.06
    NST
    0.06
    Activations Density 0.008%

    No Known Activations