© 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. 5-LLAMASCOPE-RES-131K
    11. 125975
    Prev
    Next
    INDEX
    Explanations

    the presence of specific locations and times associated with events

    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
    utt
    -0.07
    zi
    -0.07
    AMS
    -0.06
    alus
    -0.06
    AFX
    -0.06
    hed
    -0.06
    onis
    -0.06
    alore
    -0.06
    UD
    -0.06
    swick
    -0.06
    POSITIVE LOGITS
    丸
    0.08
     Fade
    0.07
    appa
    0.06
    acades
    0.06
     Açık
    0.06
    381
    0.06
    _fixture
    0.06
    289
    0.06
    228
    0.06
    ftar
    0.06
    Activations Density 0.008%

    No Known Activations