© 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. 40821
    Prev
    Next
    INDEX
    Explanations

    sections and headings in a document

    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
    ÑĥлÑİ
    -0.07
    idl
    -0.07
    kil
    -0.07
    禮
    -0.06
    -preview
    -0.06
    RIORITY
    -0.06
     à¤īल
    -0.06
     اÙĦعÙĨ
    -0.06
    fig
    -0.06
    ãģĦãģĦ
    -0.06
    POSITIVE LOGITS
    raquo
    0.09
    ispens
    0.07
    lder
    0.06
     Pill
    0.06
    Including
    0.06
    anki
    0.06
     Including
    0.06
    spacer
    0.06
    incl
    0.06
     general
    0.06
    Activations Density 0.017%

    No Known Activations