© 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. 129046
    Prev
    Next
    INDEX
    Explanations

    specific date and time information related to broadcasts

    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
     Darkness
    -0.06
     nack
    -0.06
     cinematic
    -0.06
    peaker
    -0.06
    roupon
    -0.06
    ĵ°
    -0.06
     Filme
    -0.06
    plementation
    -0.06
    -spe
    -0.06
    ÅĻej
    -0.06
    POSITIVE LOGITS
    anas
    0.07
    Assignable
    0.06
    och
    0.06
    iyon
    0.06
    ory
    0.06
    idual
    0.06
     Haus
    0.06
    drv
    0.06
    ovable
    0.06
    italic
    0.06
    Activations Density 0.010%

    No Known Activations