© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 16135
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ini
    -0.07
     overall
    -0.07
     bitten
    -0.06
    ikh
    -0.06
    534
    -0.06
    ffen
    -0.06
     Perception
    -0.06
    INI
    -0.06
     Overall
    -0.06
    .datatables
    -0.06
    POSITIVE LOGITS
    ÑĥÑĤи
    0.06
    åŃIJãģ®
    0.06
    axon
    0.06
    ÏĩÏİ
    0.06
     Barth
    0.06
     å·Ŀ
    0.06
    é§ħå¾ĴæŃ©
    0.06
    _PROTO
    0.06
    argo
    0.06
    PNG
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.