© 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. 118396
    Prev
    Next
    INDEX
    Explanations

    references to Earth and related scientific concepts

    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
    het
    -0.07
    ond
    -0.07
    ponent
    -0.07
    iddet
    -0.07
    uses
    -0.07
    оÑĢе
    -0.07
    andr
    -0.06
    otton
    -0.06
    ábado
    -0.06
    interop
    -0.06
    POSITIVE LOGITS
    quake
    0.15
    bound
    0.10
    worm
    0.10
    lings
    0.10
    ling
    0.09
     quake
    0.08
     Äijai
    0.07
    work
    0.07
    moving
    0.07
    arie
    0.07
    Activations Density 0.016%

    No Known Activations