© 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. 16802
    Prev
    Next
    INDEX
    Explanations

    instances of the word "full" and related terms indicating completeness

    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
    grim
    -0.07
    forman
    -0.07
    иÑģлов
    -0.06
    undos
    -0.06
    mour
    -0.06
     sine
    -0.06
    JECT
    -0.06
    اÙĦÙī
    -0.06
    prites
    -0.06
     __
    -0.06
    POSITIVE LOGITS
    owell
    0.06
    æĪ¿
    0.06
     اÙĦبÙĦ
    0.06
    .pref
    0.06
     Bus
    0.06
    ãĤªãĥ³
    0.06
    cent
    0.06
     township
    0.06
    ĩ
    0.06
    achuset
    0.06
    Activations Density 0.000%

    No Known Activations