© 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. 106441
    Prev
    Next
    INDEX
    Explanations

    terms related to electronic governance systems and their implementation

    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
    n
    -0.07
    h
    -0.07
    r
    -0.07
    c
    -0.06
    é
    -0.06
    d
    -0.06
    b
    -0.06
    so
    -0.06
    strup
    -0.06
    v
    -0.06
    POSITIVE LOGITS
    illisecond
    0.08
    /mobile
    0.08
    ezier
    0.07
    Ñĵ
    0.07
    &o
    0.07
     znam
    0.07
    tuk
    0.07
    å±ħæ°ij
    0.07
    ierz
    0.07
    .infinity
    0.07
    Activations Density 0.007%

    No Known Activations