© 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. 125848
    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
     duly
    -0.05
    ritt
    -0.05
     comput
    -0.05
    Ħ
    -0.05
    Hell
    -0.05
     alt
    -0.05
     Marian
    -0.05
    211
    -0.05
     Hell
    -0.05
    á½°
    -0.05
    POSITIVE LOGITS
     Erotische
    0.09
    udent
    0.08
    jvu
    0.08
    oppel
    0.08
    arken
    0.08
     frække
    0.08
     hã
    0.08
     Hüs
    0.07
    PrototypeOf
    0.07
    надлеж
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.