© 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. 84521
    Prev
    Next
    INDEX
    Explanations

    key moments of arrival and movement in a narrative

    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
    orta
    -0.07
     aks
    -0.06
    chema
    -0.06
    ldb
    -0.06
    érica
    -0.06
    ãĥĬãĥ«
    -0.06
    idor
    -0.06
    edir
    -0.06
    romise
    -0.06
    artz
    -0.06
    POSITIVE LOGITS
     ë³´ë©´
    0.08
    룰
    0.07
    expect
    0.07
     expecting
    0.07
    456
    0.06
    ento
    0.06
    156
    0.06
    pta
    0.06
    åıijçİ°
    0.06
    amet
    0.06
    Activations Density 0.029%

    No Known Activations