© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95884
    Prev
    Next
    INDEX
    Explanations

    names and titles of individuals in cultural 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
    мини
    -0.08
    arro
    -0.08
    (æ°´
    -0.08
    άÏĥ
    -0.07
    Äįek
    -0.07
     Barnett
    -0.07
     Mol
    -0.07
    ضÙĪ
    -0.07
     diseñador
    -0.07
    ằm
    -0.07
    POSITIVE LOGITS
    udi
    0.07
    imer
    0.06
       
    0.06
    iko
    0.06
    emia
    0.06
    uffer
    0.06
    acos
    0.05
    fol
    0.05
    ios
    0.05
    igo
    0.05
    Activations Density 0.017%

    No Known Activations