© 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. 93649
    Prev
    Next
    INDEX
    Explanations

    references to notable achievements or highlights within various contexts

    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
    _MAXIMUM
    -0.07
    .btnSave
    -0.06
     ÙħرÙĥز
    -0.06
    .btnClose
    -0.06
    æĸ¹
    -0.06
    èĬĿ
    -0.06
     ÙĪاÙĨ
    -0.06
     collect
    -0.06
    .btnCancel
    -0.05
    eden
    -0.05
    POSITIVE LOGITS
    ekil
    0.08
    acher
    0.08
    aeper
    0.07
    ispecies
    0.07
    akter
    0.06
    ector
    0.06
    ayah
    0.06
    embers
    0.06
    ugen
    0.06
    £½
    0.06
    Activations Density 0.005%

    No Known Activations