© 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. 16115
    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
     objectType
    -0.07
     bang
    -0.06
     contradictions
    -0.06
     subjective
    -0.06
    olve
    -0.06
    ì±Ħ
    -0.06
     Defines
    -0.06
    forma
    -0.05
     Tony
    -0.05
    ġ
    -0.05
    POSITIVE LOGITS
    orno
    0.07
     redes
    0.07
    Ñĵ
    0.07
    sian
    0.06
    ollapsed
    0.06
    heed
    0.06
    Alright
    0.06
     instances
    0.06
    é®®
    0.06
    ána
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.