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. 87560
    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
     Britain
    -0.07
     Brit
    -0.07
    ancel
    -0.06
    mrt
    -0.06
    _INCLUDED
    -0.06
    _ACL
    -0.06
    ứ
    -0.06
    oriously
    -0.06
     Barker
    -0.06
    pcodes
    -0.06
    POSITIVE LOGITS
     Irish
    0.12
    .ie
    0.10
     Ireland
    0.10
     Dublin
    0.09
     Cork
    0.09
    reland
    0.08
     Belfast
    0.07
     RTE
    0.07
     Conor
    0.07
    Ir
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.