© 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. 125933
    Prev
    Next
    INDEX
    Explanations

    terms related to legal professionals or solicitors

    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
    ane
    -0.07
    enden
    -0.07
    atrix
    -0.06
    λη
    -0.06
     (?)
    -0.06
    eda
    -0.06
     anon
    -0.06
    413
    -0.06
    /backend
    -0.06
    itters
    -0.06
    POSITIVE LOGITS
    okin
    0.08
    orz
    0.07
    été
    0.07
    jte
    0.07
    sez
    0.07
    jni
    0.06
     dá
    0.06
    seau
    0.06
    kenin
    0.06
    ickerView
    0.06
    Activations Density 0.002%

    No Known Activations