Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 93945
    Prev
    Next
    INDEX
    Explanations

    geographic locations related to academic and research institutions

    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
    dz
    -0.08
    uler
    -0.06
     "
    -0.06
    lop
    -0.06
    zt
    -0.06
     Schmidt
    -0.06
     Wid
    -0.06
     roses
    -0.06
     Observable
    -0.06
    esus
    -0.06
    POSITIVE LOGITS
     preval
    0.07
    ÙĨÙĪÛĮس
    0.07
    'gc
    0.07
    Wnd
    0.07
    .await
    0.07
    елем
    0.07
    пÑĢиклад
    0.07
    .onViewCreated
    0.07
    criptor
    0.07
     à¸Ľà¸£à¸°à¹Ģà¸Ĺศ
    0.07
    Activations Density 0.009%

    No Known Activations