© 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. 29596
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of individuals and titles

    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
    %C
    -0.07
    LARI
    -0.07
     riêng
    -0.07
    rine
    -0.07
    _ATOMIC
    -0.06
    itti
    -0.06
    (éĩij
    -0.06
    uniacid
    -0.06
    ARING
    -0.06
    &#
    -0.06
    POSITIVE LOGITS
    zelf
    0.10
    maal
    0.08
    /her
    0.07
    dech
    0.07
    -chan
    0.07
    idis
    0.06
    //(
    0.06
     doz
    0.06
    nesty
    0.06
     mastur
    0.06
    Activations Density 0.173%

    No Known Activations