© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 128492
    Prev
    Next
    INDEX
    Explanations

    statements related to news reporting and updates on violence or attacks

    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
    Ł
    -0.07
    asso
    -0.07
    302
    -0.06
    cken
    -0.06
    cai
    -0.06
    _vk
    -0.06
    521
    -0.06
    anh
    -0.06
    iah
    -0.06
    roy
    -0.06
    POSITIVE LOGITS
     comp
    0.07
    adolu
    0.07
    iyon
    0.07
    anki
    0.06
    .xhtml
    0.06
    UNET
    0.06
    еÑģп
    0.06
    rac
    0.06
     Fay
    0.06
    tiv
    0.06
    Activations Density 0.014%

    No Known Activations