Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4378
    Prev
    Next
    INDEX
    Explanations

    academic disciplines and fields of study related to science

    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
    ̧
    -0.08
    éal
    -0.07
    arith
    -0.07
     ún
    -0.07
    atee
    -0.07
    midt
    -0.07
    rá
    -0.07
    ookies
    -0.07
     dve
    -0.06
    uem
    -0.06
    POSITIVE LOGITS
    Tomorrow
    0.06
     Today
    0.06
    uj
    0.06
    fun
    0.06
    ka
    0.06
    preh
    0.06
    today
    0.06
     Hoy
    0.06
    -of
    0.06
     hoy
    0.06
    Activations Density 0.047%

    No Known Activations